INDEX

Explanations

scraped text from scientific publications, including author names, titles, and years

oai_token-act-pair · gemini-2.0-flash

publications

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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



-0.68

expandindo

-0.68

 snippetHide

-0.66

-0.63

 estekak

-0.61

 surla

-0.57

sizeCache

-0.57

 فريبيس

-0.56

SerializedSize

-0.55

thâu

-0.54

POSITIVE LOGITS

最快更新

0.60

✨:

0.53

lagi

0.50

likle

0.45

 InputDecoration

0.45

IgnoreCase

0.43

bosis

0.43

');?>

0.42

rrggbb

0.42

Hozzáférés

0.41

Activations Density 1.029%

scraped text from scientific publications, including author names, titles, and years

publications

No Comments

No Known Activations