INDEX

Explanations

the word "face" and words derived from it

oai_token-act-pair · gemini-2.0-flash

face

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

 AssemblyCompany

-0.53

nic

-0.46

PRNewswire

-0.45

sum

-0.45

Res

-0.45

 tracts

-0.43

ServletException

-0.42

res

-0.41

omb

-0.39

 kasarigan

-0.39

POSITIVE LOGITS

Personensuche

0.87

esModule

0.79

NOPQRST

0.78

utives

0.75

 للمعارف

0.73

WebVitals

0.66

IsMutable

0.64

chnet

0.63

 كومونز

0.62

 intStringLen

0.61

Activations Density 1.532%

the word "face" and words derived from it

face

No Comments

No Known Activations