INDEX

Explanations

code blocks that look like they are autogenerated

oai_token-act-pair · gemini-2.0-flash

code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 getopt

-0.50

ScopeManager

-0.50

 clandestine

-0.50

ReusableCell

-0.48

ม้

-0.47

pyrid

-0.46

Ancient

-0.46

StoreMessageInfo

-0.45

libft

-0.44

 ErrIntOverflow

-0.44

POSITIVE LOGITS

<bos>

0.83

 beginnetje

0.75

Билгалдахарш

0.67

Bronnen

0.67

 виправивши

0.65

 ostavi

0.65

Tembelea

0.64

GEBURTSDATUM

0.64

 HasFactory

0.63

 linkovi

0.62

Activations Density 1.598%

code blocks that look like they are autogenerated

code

No Comments

No Known Activations