INDEX

Explanations

mentions of Java code or errors

oai_token-act-pair · gemini-2.0-flash

java

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 فريبيس

-0.72

principalColumn

-0.63

clable

-0.59

 مرئيه

-0.56

ItemBackground

-0.56

Lähteet

-0.53

 AssemblyCompany

-0.52

 مشين

-0.52

 odkazy

-0.52

 Wikispecies

-0.52

POSITIVE LOGITS

ScopeManager

0.59

 intptr

0.50

 Montmartre

0.49

يكا

0.49

URG

0.46

viewDidLoad

0.46

enderita

0.45

Erst

0.45

MPR

0.44

án

0.44

Activations Density 0.537%

mentions of Java code or errors

java

No Comments

No Known Activations