INDEX

Explanations

SQL code and related terms

oai_token-act-pair · gemini-2.0-flash

@

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

setLayoutManager

-0.58

 pâtes

-0.50

 aktivitet

-0.49

 trouverez

-0.49

 religieuses

-0.47

 sguardo

-0.47

 industriels

-0.47

Географи

-0.47

 barnen

-0.47

 ligação

-0.46

POSITIVE LOGITS

 ModelExpression

0.69

styleType

0.65

աբ

0.62

resizingMask

0.59

 Mank

0.59

Manbalar

0.59

 AssemblyProduct

0.57

llac

0.56

interopRequire

0.56

SOUNDBITE

0.56

Activations Density 1.443%

SQL code and related terms

@

No Comments

No Known Activations