INDEX

Explanations

terms related to a wide variety of specific fields

oai_token-act-pair · gemini-2.0-flash

"format" and translations

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 CreateTagHelper

-0.91

NameInMap

-0.63

帖最后由

-0.62

VideoCapture

-0.56

LookAnd

-0.56

MigrationBuilder

-0.56

 unknownFields

-0.54

farwyddwr

-0.54

 Fath

-0.54

-0.53

POSITIVE LOGITS

 format

0.74

形式

0.64

 formato

0.60

 form

0.56

UnsafeEnabled

0.54

狀

0.54

 Autorizaciones

0.54

형

0.53

 formatos

0.51

principalTable

0.51

Activations Density 2.937%

terms related to a wide variety of specific fields

"format" and translations

No Comments

No Known Activations