INDEX

Explanations

calls to action to leave a comment

oai_token-act-pair · gemini-2.0-flash

invites comments

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

+#+#

-0.68

 <<<<<<<<<<<<<<

-0.66

saraba

-0.63

AndEndTag

-0.63

SharedCtor

-0.62

 surla

-0.60

 الحره

-0.59

новниш

-0.59

FormTagHelper

-0.57

KURZBESCHREIBUNG

-0.57

POSITIVE LOGITS

 jsPsych

0.51

ffiche

0.50

 знаешь

0.48

antMatchers

0.48

 hoek

0.46

 Freire

0.45

 dirigé

0.44

 jurk

0.44

 telefoon

0.43

 renforcé

0.43

Activations Density 0.321%

calls to action to leave a comment

invites comments

No Comments

No Known Activations