INDEX

Explanations

idioms and metaphors

oai_token-act-pair · gemini-2.0-flash

head or foot wear

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

 råd

-0.50

 erős

-0.49

 Schenk

-0.48

 forbindelse

-0.47

 vreme

-0.45

frente

-0.44

 stå

-0.44

 őket

-0.43

 Vainqueur

-0.43

 sexe

-0.43

POSITIVE LOGITS

hat

1.21

 hats

1.15

hats

0.96

 shoes

0.90

HAT

0.84

 Hats

0.82

Hat

0.82

cap

0.79

 caps

0.78

shoes

0.78

Activations Density 0.575%

idioms and metaphors

head or foot wear

No Comments

No Known Activations