INDEX

Explanations

code snippets

oai_token-act-pair · gemini-2.0-flash

Code snippets

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

Personendaten

-0.67

EDEFAULT

-0.66

oredCriteria

-0.59

 PeEnEo

-0.58

DispatchToProps

-0.56

adaptiveStyles

-0.55

 يتيمه

-0.54

abestanden

-0.52

 Roskov

-0.52

 AssemblyVersion

-0.51

POSITIVE LOGITS

archiviato

0.51

 становника

0.51

QUIR

0.50

LookAnd

0.49

ynchrotron

0.48

GeneratedCode

0.47

 लगा

0.47

tamide

0.47

 oprot

0.47

 Turnpike

0.46

Activations Density 1.426%

code snippets

Code snippets

No Comments

No Known Activations