Feature request: Allow passing in scope for TransformedVariable, DeferredTensor for distributed programming

[jcalifornia]

From here: https://groups.google.com/a/tensorflow.org/g/tfprobability/c/_9EuU3FnErY/m/cpNQENy6AQAJ

2. Re: distributed programming: I think your change would be a great addition to TransformedVariable (and possible DeferredTensor).

A quick and dirty hack is to pass the scope into the constructor:

class TransformedVariable(tfp_util.TransformedVariable):
    def __init__(self, initial_value, bijector,
                 dtype=None, scope=None, name=None, **kwargs):