INDEX

Explanations

words related to geometric location and neighbors, and code

oai_token-act-pair · gemini-2.0-flash

image processing algorithms

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

 betweenstory

-0.55

rawDesc

-0.52

GraphicsUnit

-0.50

ollectionView

-0.50

ORTH

-0.49

URATION

-0.48

ANTLR

-0.47

leet

-0.47

 OnInit

-0.47

页面存档备份

-0.47

POSITIVE LOGITS

dafx

0.58

Parcelize

0.56

enterOuterAlt

0.55

Datuak

0.51

DeleteBehavior

0.50

IPAC

0.50

 يتيمه

0.50

migrationBuilder

0.50

SocketChannel

0.49

gonic

0.47

Activations Density 3.636%

words related to geometric location and neighbors, and code

image processing algorithms

No Comments

No Known Activations

words related to geometric location and neighbors, and code

image processing algorithms

No Comments

No Known Activations