INDEX

Explanations

terms related to internet activity

oai_token-act-pair · gemini-2.0-flash

online

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 online

-1.02

online

-0.93

 Online

-0.89

Online

-0.86

ONLINE

-0.81

 ONLINE

-0.81

لكتر

-0.63

 онлайн

-0.63

オンライン

-0.61

อนไลน์

-0.61

POSITIVE LOGITS

 ProtoMessage

0.62

 estekak

0.61

annique

0.59

ContentAsync

0.57

 UIKit

0.57

webElementXpaths

0.55

Билгалдахарш

0.55

lgari

0.54

 חיצוניים

0.54

 BoxFit

0.51

Activations Density 7.434%

terms related to internet activity

online

No Comments

No Known Activations