INDEX

Explanations

bracketed numbers, which probably represent legal citations

oai_token-act-pair · gemini-2.0-flash

footnotes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

普遍

-0.42

ebi

-0.42

-0.41

-0.40

 poire

-0.40

documentElement

-0.39

 dịch

-0.38

is

-0.38

of

-0.38

lic

-0.38

POSITIVE LOGITS

 تضيفلها

1.04

LookAnd

0.97

queryInterface

0.92

SharedDtor

0.92

featureID

0.91

writeFieldEnd

0.90

 سكانية

0.90

StoryboardSegue

0.89

MigrationBuilder

0.86

Jeografia

0.85

Activations Density 3.105%

bracketed numbers, which probably represent legal citations

footnotes

No Comments

No Known Activations