INDEX

Explanations

the word 'blog' and related words, especially 'post', and also the word 'conference'

oai_token-act-pair · gemini-2.0-flash

blog

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

 فريبيس

-0.70

gogo

-0.66

 الدولى

-0.63

acité

-0.62

entials

-0.62

WebElementEntity

-0.61

/\.

-0.60

UserScript

-0.59

 Réponses

-0.59

Filmografie

-0.59

POSITIVE LOGITS

SharedCtor

0.71

featureID

0.56

sidemargin

0.52

+#+#

0.50

tagHelperRunner

0.48

 waard

0.44

Acest

0.43

kháu

0.42

 migrator

0.41

 casó

0.41

Activations Density 0.782%

the word 'blog' and related words, especially 'post', and also the word 'conference'

blog

No Comments

No Known Activations