INDEX

Explanations

questions and answers, headings or categories, references, code snippets, and links, i.e., segments from digital documents

oai_token-act-pair · gemini-2.0-flash

start of new article

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 nakalista

-0.61

ThroughAttribute

-0.52

 welcome

-0.49

olari

-0.48

ellyn

-0.46

 saites

-0.46

ViewFeatures

-0.46

 nahilalakip

-0.44

idom

-0.44

<eos>

-0.43

POSITIVE LOGITS

 referrerpolicy

0.81

Zitat

0.62

("")]

0.62

 }}$}

0.61

--}}

0.59

')}}

0.58

تحميل

0.57

Wichtig

0.57

'])){

0.57

Răsp

0.57

Activations Density 13.283%

questions and answers, headings or categories, references, code snippets, and links, i.e., segments from digital documents

start of new article

No Comments

No Known Activations