INDEX

Explanations

references to language, dialects, and linguistics

oai_token-act-pair · gemini-2.0-flash

language

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 language

-0.56

 langue

-0.55

 Wiktionnaire

-0.55

JspWriter

-0.51

LookAnd

-0.50

 Langue

-0.49

ởi

-0.46

 Sprache

-0.45

ABILIDAD

-0.43

Tazama

-0.43

POSITIVE LOGITS

CloseOperation

0.66

BeginContext

0.63

UserScript

0.61

ArgsConstructor

0.61

 utafitiHapana

0.60

 LUMP

0.59

DockStyle

0.59

Kjelder

0.59

 forState

0.59

<?,

0.58

Activations Density 1.586%

references to language, dialects, and linguistics

language

No Known Activations