INDEX

Explanations

phrases that describe small quantities, touches, or actions, sometimes in a whimsical or figurative manner.

oai_token-act-pair · gemini-2.0-flash

French language

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 ModelExpression

-0.73

awaiter

-0.71

出版年

-0.69

sibirsk

-0.65

NameInMap

-0.62

VideoCapture

-0.61

 ActiveRecord

-0.56

kheim

-0.55

EndProject

-0.55

Personensuche

-0.54

POSITIVE LOGITS

bit

0.82

bit

0.75

 little

0.71

 biß

0.71

little

0.71

BIT

0.69

 LITTLE

0.69

 bisschen

0.68

 Little

0.66

 beetje

0.66

Activations Density 0.673%

phrases that describe small quantities, touches, or actions, sometimes in a whimsical or figurative manner.

French language

No Known Activations