INDEX

Explanations

words or phrases related to Judaism, Israel, Jewish people, or antisemitism, and sometimes more general references to paganism or religion

oai_token-act-pair · gemini-2.0-flash

Jewish

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

 Jewish

-0.84

Jewish

-0.76

Rabbi

-0.54

 Christian

-0.54

 Jews

-0.53

Christian

-0.53

 Rabbi

-0.52

 jewish

-0.51

jewish

-0.50

 Judaism

-0.49

POSITIVE LOGITS

 propOrder

0.90

 NSCoder

0.89

ScopeManager

0.85

OGND

0.83

:✨

0.77

complexContent

0.75

 متعلقه

0.75

клопе

0.74

 lenker

0.74

 wireType

0.73

Activations Density 7.750%

words or phrases related to Judaism, Israel, Jewish people, or antisemitism, and sometimes more general references to paganism or religion

Jewish

No Comments

No Known Activations