INDEX

Explanations

nouns indicating formal documents, published works, or changes in government

oai_token-act-pair · gemini-2.0-flash

legal, scientific documents

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للاسماء

-0.54

Zodiac

-0.54

 متعلقه

-0.53

wikidata

-0.53

sû

-0.51

 Zodiac

-0.49

GHIJKLM

-0.48

 église

-0.48

odom

-0.48

 Wojciech

-0.48

POSITIVE LOGITS

TintMode

0.79

DockStyle

0.60

ContentAsync

0.59

 BoxDecoration

0.59

PositiveButton

0.55

typeorm

0.53

AnchorTagHelper

0.52

migrationBuilder

0.51

InputBorder

0.51

########.

0.51

Activations Density 1.709%

nouns indicating formal documents, published works, or changes in government

legal, scientific documents

No Comments

No Known Activations