INDEX

Explanations

words relating to domesticity and settling down

oai_token-act-pair · gemini-2.0-flash

head

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

+#+

-0.70

новниш

-0.62

Uwagi

-0.55

 оригіналу

-0.54

foreignKey

-0.52

 SIMBAD

-0.52

üyada

-0.50

rophes

-0.50

 الدولى

-0.49

 past

-0.49

POSITIVE LOGITS

head

0.67

 heads

0.67

heads

0.65

 head

0.64

LookAnd

0.57

Personendaten

0.53

 Heads

0.52

Head

0.50

Heads

0.50

頭

0.49

Activations Density 0.813%

words relating to domesticity and settling down

head

No Comments

No Known Activations