INDEX

Explanations

code snippets and possibly markup

oai_token-act-pair · gemini-2.0-flash

code characters

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

<bos>

-0.97

/**

-0.55

-0.53

ibr

-0.48

 tslint

-0.46

 parem

-0.46

 trade

-0.44

 eslint

-0.44

 فريبيس

-0.44

est

-0.44

POSITIVE LOGITS

 propOrder

0.83

Przypisy

0.80

 betweenstory

0.79

IVEREF

0.79

حياته

0.76

RegressionTest

0.73

 للاسماء

0.73

MessageTagHelper

0.69

 trajets

0.68

verifyException

0.68

Activations Density 3.421%

code snippets and possibly markup

code characters

No Comments

No Known Activations

code snippets and possibly markup

code characters

No Comments

No Known Activations