INDEX

Explanations

the word "data" in code snippets

oai_token-act-pair · gemini-2.0-flash

data

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 data

-1.73

data

-1.44

 Data

-1.28

Data

-1.21

数据

-1.09

 DATA

-1.09

データ

-1.08

 Daten

-1.07

DATA

-1.00

數據

-1.00

POSITIVE LOGITS

RenderAtEndOf

0.72

ioutil

0.67

 BoxDecoration

0.65

 StatelessWidget

0.62

XmlAccessorType

0.60

 brancas

0.60

 callers

0.60

PreExecute

0.60

нрави

0.59

 ExecuteAsync

0.59

Activations Density 0.211%

the word "data" in code snippets

data

No Comments

No Known Activations