INDEX

Explanations

words beginning with "ex" followed by one or two more letters

oai_token-act-pair · gemini-2.0-flash

ex

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ufig

-0.53

Encyklopedia

-0.52

 unitary

-0.52

atized

-0.51

WANTED

-0.49

TAGS

-0.48

 Reverso

-0.47

vantages

-0.47

FINED

-0.46

BagLayout

-0.46

POSITIVE LOGITS

IsMutable

0.63

reactivex

0.54

 <=",

0.53

ClientSize

0.51

Personendaten

0.51

 douce

0.50

 Wikimedijinoj

0.50

aminen

0.48

ForRow

0.48

squeeze

0.47

Activations Density 0.302%

words beginning with "ex" followed by one or two more letters

ex

No Comments

No Known Activations