INDEX

Explanations

texts discussing historical events, political controversy, or legal offenses

oai_token-act-pair · gemini-2.0-flash

formal writing

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 disegni

-0.56

Servus

-0.52

ographia

-0.49

Билгалдахарш

-0.49

 disegno

-0.48

 circonstances

-0.48

Coordonnées

-0.47

 Schreib

-0.47

rungsseite

-0.47

ViewImports

-0.46

POSITIVE LOGITS

RectangleBorder

0.77

 CreateTagHelper

0.65

 defaultstate

0.63

 onCancelled

0.58

 betweenstory

0.58

 TextAlign

0.55

TintMode

0.53

ंदीखरीदारी

0.51

 متعلقه

0.50

JsonProperty

0.50

Activations Density 1.091%

texts discussing historical events, political controversy, or legal offenses

formal writing

No Known Activations