INDEX

Explanations

words and phrases associated with scientific or experimental data and analysis

oai_token-act-pair · gemini-2.0-flash

experimental backgrounds/components

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

 виправивши

-0.55

 krav

-0.53

AddHtmlAttribute

-0.48

/*

-0.48

+#+

-0.47

ppure

-0.45

handeling

-0.45

 acompanhar

-0.45

 Tapatalk

-0.45

yw

-0.45

POSITIVE LOGITS

Personendaten

0.78

<tfoot>

0.69

EReference

0.62

Уважа

0.57

')));

0.57

 الحره

0.56

sunter

0.55

PostExecute

0.54

MockBean

0.54

')):

0.53

Activations Density 4.810%

words and phrases associated with scientific or experimental data and analysis

experimental backgrounds/components

No Comments

No Known Activations