INDEX

Explanations

possessive pronouns

oai_token-act-pair · gemini-2.0-flash

family relationships

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

OGND

-0.94

LookAnd

-0.84

GEBURTS

-0.78

MethodManager

-0.76

GEBURTSDATUM

-0.73

出版年

-0.71

 архивлан

-0.69

 Meksiku

-0.69

دانشنامهٔ

-0.69

 otomatig

-0.68

POSITIVE LOGITS

 loving

0.47

 driving

0.43

des

0.43

 nhiêu

0.42

 love

0.42

 partner

0.41

 belief

0.41

der

0.40

 best

0.40

Activations Density 0.141%

possessive pronouns

family relationships

No Comments

No Known Activations