INDEX

Explanations

words related to completing some process or goal

oai_token-act-pair · gemini-2.0-flash

technical descriptions

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

 مشين

-0.81

CppCodeGen

-0.64

 ویکی‌پدیا

-0.63

 AppCompatTheme

-0.61

Hauptartikel

-0.59

ürtel

-0.56

 Chwiliwch

-0.54

__':

-0.52

 rempliss

-0.52

 comprennent

-0.51

POSITIVE LOGITS

 working

0.82

 taken

0.79

 operating

0.69

 nahilalakip

0.65

 sitting

0.64

 held

0.63

Билгалдахарш

0.62

mers

0.59

 stuck

0.59

 serving

0.57

Activations Density 5.844%

words related to completing some process or goal

technical descriptions

No Comments

No Known Activations