INDEX

Explanations

names with unusual characters and formatting, possibly of Eastern European or Asian origin, and words associated with charts, football teams, and sports, including terms like "footballer," "manager," and "coach"

oai_token-act-pair · 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

jir

-0.65

 stanovnika

-0.60

HostException

-0.59

Географиясе

-0.54

ucket

-0.54

ÓS

-0.53

Sinopse

-0.52

 endregion

-0.50

 препратки

-0.50

ogaster

-0.49

POSITIVE LOGITS

原始内容存档于

0.78

 Normdatei

0.75

 незавершена

0.72

GEBURTSDATUM

0.71

 resourceCulture

0.69

AndEndTag

0.68

ⓧ

0.66

ərbaycan

0.65

 للاسماء

0.62

InjectAttribute

0.60

Activations Density 26.880%

names with unusual characters and formatting, possibly of Eastern European or Asian origin, and words associated with charts, football teams, and sports, including terms like "footballer," "manager," and "coach"

No Known Activations

names with unusual characters and formatting, possibly of Eastern European or Asian origin, and words associated with charts, football teams, and sports, including terms like "footballer," "manager," and "coach"

No Known Activations