INDEX

Explanations

a mix of Malaysian language and number-related content

oai_token-act-pair · gemini-2.0-flash

Southeast Asian Languages

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

verwijspagina

-0.57

 الرياضيه

-0.55

LookAnd

-0.52

bibnamefont

-0.52

digitalWrite

-0.52

BibitemShut

-0.51

bibinfo

-0.51

 itſelf

-0.50

 ویکی‌پدیای

-0.50

 myſelf

-0.49

POSITIVE LOGITS

ništvo

0.54

OfWeek

0.54

 pady

0.50

 pompe

0.48

<?,

0.48

ghana

0.47

 Periodicals

0.47

тербург

0.46

kasse

0.46

 Yorke

0.46

Activations Density 0.590%

a mix of Malaysian language and number-related content

Southeast Asian Languages

No Comments

No Known Activations