INDEX

Explanations

text related to results being based on underlying principles

oai_token-act-pair · gemini-2.0-flash

base

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 based

-1.12

 Based

-1.06

Based

-1.00

based

-0.99

 basis

-0.97

 basados

-0.90

BASED

-0.88

 baseado

-0.87

 basadas

-0.87

 BASED

-0.87

POSITIVE LOGITS

DockStyle

0.73

 estekak

0.61

Hozzáférés

0.58

 AssemblyCulture

0.58

ایج

0.57

adaptiveStyles

0.57

 BorderSide

0.56

Décès

0.56

enterOuterAlt

0.55

Coordenadas

0.54

Activations Density 15.653%

text related to results being based on underlying principles

base

No Comments

No Known Activations