INDEX

Explanations

words and phrases related to experimental validation and numerical simulation, especially within scientific publications

oai_token-act-pair · gemini-2.0-flash

predicts

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

 further

-0.48

indade

-0.47

 dedicated

-0.46

нан

-0.46

aternion

-0.43

hode

-0.43

luca

-0.42

⇌

-0.42

SqlQuery

-0.42

azaki

-0.42

POSITIVE LOGITS

tagHelperRunner

0.87

 AssemblyCulture

0.86

bootstrapcdn

0.79

InjectAttribute

0.78

makeConstraints

0.70

 تضيفلها

0.69

.*")]

0.69

 Réponses

0.69

///</

0.66

findpost

0.65

Activations Density 3.824%

words and phrases related to experimental validation and numerical simulation, especially within scientific publications

predicts

No Comments

No Known Activations