INDEX

Explanations

context related to words/language and their meanings or usages

oai_token-act-pair · gemini-2.0-flash

Word definitions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

كويكب

-0.81

nestjs

-0.75

BeginContext

-0.75

帖最后由

-0.70

mybatisplus

-0.70

TypedDataSet

-0.69

SerializedName

-0.69

SuppressLint

-0.69

 createContext

-0.66

migrationBuilder

-0.66

POSITIVE LOGITS

发表于

0.45

Subviews

0.44

 виправивши

0.43

 équ

0.38

 mennes

0.36

kegaard

0.35

 jiwa

0.33

 børn

0.33

yum

0.33

 mennesker

0.33

Activations Density 43.090%

context related to words/language and their meanings or usages

Word definitions

No Comments

No Known Activations