INDEX

Explanations

architecture and design.

oai_token-act-pair · gemini-2.0-flash

architecture

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 programação

-0.60

-0.59

 spese

-0.56

 remporté

-0.55

 positifs

-0.53

-0.52

 manifestazione

-0.52

 cerimonia

-0.50

 giudi

-0.49

 internazionali

-0.48

POSITIVE LOGITS

 CanadaChoose

1.09

 snippetHide

1.09

ⓧ

0.96

 שוליים

0.93

 "..\..\

0.93

oredCriteria

0.93

Personensuche

0.92

UnitTesting

0.88

 nahilalakip

0.87

principalTable

0.86

Activations Density 1.849%

architecture and design.

architecture

No Comments

No Known Activations