INDEX

Explanations

words, ideas, and phrases associated with social sciences, especially sociology and cultural studies, including race, class, gender, and political criticism.

oai_token-act-pair · gemini-2.0-flash

social issues

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

 оригіналу

-0.69

 Balboa

-0.69

,$_

-0.66

 Hamma

-0.66

 itſelf

-0.65

 مرئيه

-0.65

__":

-0.65

 purpoſe

-0.65

 ་་

-0.64

 Piccadilly

-0.64

POSITIVE LOGITS

 negativas

0.51

 erős

0.49

 périph

0.48

 esetben

0.47

 Meksiku

0.47

 jellemző

0.46

 positivas

0.46

EDEFAULT

0.44

참고

0.44

 nødvendig

0.43

Activations Density 3.425%

words, ideas, and phrases associated with social sciences, especially sociology and cultural studies, including race, class, gender, and political criticism.

social issues

No Known Activations

words, ideas, and phrases associated with social sciences, especially sociology and cultural studies, including race, class, gender, and political criticism.

social issues

No Known Activations