INDEX

Explanations

the word "and" along with filler words

oai_token-act-pair · gemini-2.0-flash

and

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Personensuche

-0.69

 sanitaires

-0.63

 médicaux

-0.62

 unknownFields

-0.57

 echi

-0.57

 culturali

-0.56

 culturelles

-0.56

打了

-0.53

 >=",

-0.53

 irré

-0.52

POSITIVE LOGITS

StoryboardSegue

0.71

writeFieldEnd

0.64

HostException

0.64

 فريبيس

0.59

FileDialog

0.59

*}[

0.58

setVerticalGroup

0.53

 otomatig

0.52

AccessFile

0.52

mybatisplus

0.50

Activations Density 2.233%

the word "and" along with filler words

and

No Comments

No Known Activations