INDEX

Explanations

words associated with human behavior and interpersonal actions, including both positive and negative conduct and interactions.

oai_token-act-pair · gemini-2.0-flash

sexual

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

 peme

-0.54

lett

-0.52

Pageable

-0.51

Bus

-0.49

Bu

-0.47

Bus

-0.47

ies

-0.47

 montée

-0.47

bus

-0.46

Boy

-0.46

POSITIVE LOGITS

Personendaten

0.98

 ModelExpression

0.84

Hauptartikel

0.75

DoubleQuotes

0.71

featureID

0.68

DeleteBehavior

0.68

KommentareTeilen

0.67

tvguidetime

0.66

 مشين

0.65

 MainAxisSize

0.63

Activations Density 2.298%

words associated with human behavior and interpersonal actions, including both positive and negative conduct and interactions.

sexual

No Comments

No Known Activations