INDEX

Explanations

instances of observations or studies being done

oai_token-act-pair · gemini-2.0-flash

observation

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 فريبيس

-0.78

gatsby

-0.74

twimg

-0.73

utrition

-0.57

teden

-0.56

Frosty

-0.56

ageable

-0.54

"]["

-0.54

 Chir

-0.53

istoitu

-0.53

POSITIVE LOGITS

Personendaten

0.60

parsedMessage

0.54

 StatelessWidget

0.50

ControllerAdvice

0.50

 Voyez

0.47

 Económica

0.47

 StatefulWidget

0.45

SpringRunner

0.44

RetentionPolicy

0.44

ViewChild

0.44

Activations Density 1.851%

instances of observations or studies being done

observation

No Comments

No Known Activations