INDEX

Explanations

the word "engagement" or its related verb forms.

oai_token-act-pair · gemini-2.0-flash

engagement

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

passo

-0.72

 endregion

-0.71

 cappello

-0.66

 canst

-0.63

 samlet

-0.61

 fantasma

-0.60

 aprend

-0.60

tencent

-0.60

 aeros

-0.59

libatkan

-0.59

POSITIVE LOGITS

DeleteBehavior

0.69

 saites

0.68

 only

0.66

AnchorStyles

0.65

sizeCache

0.64

 مشين

0.62

so

0.61

 kling

0.61

 jadx

0.61

DebuggerStep

0.61

Activations Density 0.766%

the word "engagement" or its related verb forms.

engagement

No Comments

No Known Activations