INDEX

Explanations

proper nouns, especially names of people and places

oai_token-act-pair · gemini-2.0-flash

retired professions

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 africains

-0.52

Skocz

-0.44

estars

-0.42

Према

-0.41

 Larger

-0.41

 acceptance

-0.41

Larger

-0.40

 生命周期

-0.40

 fédé

-0.40

={`/

-0.40

POSITIVE LOGITS

 retired

1.09

 housewife

0.92

 reti

0.83

 teacher

0.82

Retired

0.82

retired

0.82

 Retired

0.78

 homemaker

0.75

RUnlock

0.75

 unemployed

0.75

Activations Density 2.017%

proper nouns, especially names of people and places

retired professions

No Comments

No Known Activations