INDEX

Explanations

code snippets in various programming languages

oai_token-act-pair · gemini-2.0-flash

code snippets

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

enumi

-0.73

ArgsConstructor

-0.60

AndroidJUnit

-0.59

IsContent

-0.57

HideFlags

-0.55

-0.53

unhofer

-0.53

BagConstraints

-0.52

rungsseite

-0.50

ForRow

-0.50

POSITIVE LOGITS

 Seventeenth

0.58

frastructure

0.56

ThroughAttribute

0.55

 surla

0.54

 JADX

0.53

⑦

0.52

出版年

0.52

 *)__

0.50

 myco

0.49

 屋根

0.49

Activations Density 0.528%

code snippets in various programming languages

code snippets

No Comments

No Known Activations