INDEX

Explanations

code-related terms, especially related to licenses and software configurations

oai_token-act-pair · gemini-2.0-flash

fusion

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

XMLSchema

-0.84

 متعلقه

-0.78

 Administrativna

-0.74

 ویکی‌پدی

-0.69

GOTREF

-0.68

QMetaType

-0.66

adaptiveStyles

-0.65

 Paglinawan

-0.65

msgTypes

-0.63

MigrationBuilder

-0.62

POSITIVE LOGITS

findpost

0.50

ां

0.45

gique

0.44

bcryptjs

0.44

OneToMany

0.42

 pály

0.42

ngrx

0.42

Art

0.41

jspx

0.41

RELATIVE

0.41

Activations Density 2.434%

code-related terms, especially related to licenses and software configurations

fusion

No Comments

No Known Activations