INDEX

Explanations

words and phrases related to data collection and user information

oai_token-act-pair · gemini-2.0-flash

data privacy

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

Not in Any Lists

No Comments

Negative Logits

 للاسماء

-0.90

 للمعارف

-0.89

ThemeOverlay

-0.74

SharedCtor

-0.71

aarrggbb

-0.69

uxxxx

-0.68

setVerticalGroup

-0.66

Rhestr

-0.60

évaluateur

-0.59

 CURIAM

-0.57

POSITIVE LOGITS

 bēr

0.50

UpInside

0.47

}`}>

0.45

huri

0.45

Архівовано

0.45

ayage

0.44

اقرأ

0.44

 kasarigan

0.44

 tròn

0.43

 radians

0.43

Activations Density 1.301%

words and phrases related to data collection and user information

data privacy

No Comments

No Known Activations