INDEX

Explanations

gibberish

oai_token-act-pair · gemini-2.0-flash

French words or terms

np_token-act-pair-logits · gpt-4o-mini

Creative writing excerpts

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

findpost

-0.69

 HasFactory

-0.58

baix

-0.54

AddTagHelper

-0.54

StoryboardSegue

-0.53

Спасылкі

-0.50

ModelSerializer

-0.50

memoized

-0.48

"],

-0.48

انجليز

-0.48

POSITIVE LOGITS

 lumineuse

0.64

 hvorfor

0.56

 ISNI

0.55

RenderAtEndOf

0.53

TagMode

0.53

why

0.52

 peindre

0.52

 tromper

0.51

 optique

0.50

 privées

0.50

Activations Density 0.305%

gibberish

French words or terms

Creative writing excerpts

No Comments

No Known Activations