INDEX

Explanations

code blocks, likely in Java or C#, using curly braces and indentation

oai_token-act-pair · gemini-2.0-flash

Code-related terms

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 languages

-0.78

Languages

-0.66

 Languages

-0.66

 resourceCulture

-0.65

 language

-0.63

language

-0.62

languages

-0.60

 formats

-0.57

Language

-0.56

語言

-0.54

POSITIVE LOGITS

enterOuterAlt

0.69

tagHelperRunner

0.64

UseVisualStyle

0.62

execSQL

0.60

AndEndTag

0.58

zog

0.58

بوابة

0.58

Personensuche

0.56

 himo

0.56

tison

0.55

Activations Density 1.078%

code blocks, likely in Java or C#, using curly braces and indentation

Code-related terms

No Comments

No Known Activations