INDEX

Explanations

words related to politics and government

oai_token-act-pair · gemini-2.0-flash

Fields of work

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

AutoScaleMode

-0.60

 مرئيه

-0.54

 patients

-0.50

OGND

-0.50

 patient

-0.49

Personensuche

-0.49

Gov

-0.48

oa̍t

-0.48

出版年

-0.46

 paciente

-0.44

POSITIVE LOGITS

 education

0.88

 health

0.86

health

0.80

education

0.78

 tourism

0.74

 sports

0.74

 Health

0.71

Health

0.69

 commerce

0.68

 agriculture

0.68

Activations Density 2.314%

words related to politics and government

Fields of work

No Comments

No Known Activations