INDEX

Explanations

approval and permission

oai_token-act-pair · gemini-2.0-flash

agreement

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

))){

-0.60

Revenir

-0.55

++]=

-0.53

ТЕЛЬ

-0.51

 &___

-0.51

vince

-0.49

GeneratedValue

-0.49

retin

-0.48

MENAFN

-0.48

hasis

-0.47

POSITIVE LOGITS

 nice

0.56

↘

0.55

 Paglinawan

0.54

찮

0.53

Nice

0.53

Спољашње

0.53

PostExecute

0.53

 ویکی‌پدی

0.52

Mid

0.52

RenderAtEndOf

0.52

Activations Density 1.489%

approval and permission

agreement

No Comments

No Known Activations