INDEX

Explanations

words and phrases related to analysis, information, and opinions

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 taget

-0.37

话

-0.36

catch

-0.36

acetate

-0.36

ophosphate

-0.35

cron

-0.34

去了

-0.34

 Partagez

-0.32

 تص

-0.32

 catch

-0.32

POSITIVE LOGITS

StoryboardSegue

0.96

ArrowToggle

0.92

-};

0.87

@"/

0.86

 Réponses

0.85

 للاسماء

0.84

IsContent

0.84

\{\\

0.84

 AspNetCore

0.83

 estekak

0.81

Activations Density 17.261%

words and phrases related to analysis, information, and opinions

No Comments

No Known Activations