INDEX

Explanations

names of academic disciplines and related terms such as "init" and "/".

oai_token-act-pair · gemini-2.0-flash

code and equations

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 resourceCulture

-0.80

 Monfieur

-0.78

Personensuche

-0.77

 Paglinawan

-0.76

ⓧ

-0.76

OGND

-0.73

 Perſ

-0.69

\{\\

-0.69

MessageOf

-0.68

 Inſ

-0.66

POSITIVE LOGITS

IsContent

0.48

大利

0.47



0.46

збе

0.45

LikeLike

0.45

fu

0.45

Faz

0.44

 mesure

0.43

0.42

proud

0.42

Activations Density 0.031%

names of academic disciplines and related terms such as "init" and "/".

code and equations

No Comments

No Known Activations