INDEX

Explanations

code syntax such as boolean operators, assignment operators, and parentheses

oai_token-act-pair · gemini-2.0-flash

punctuation

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 متعلقه

-0.67

ynchronously

-0.66

msgTypes

-0.64

XmlSchema

-0.64

AsUp

-0.62

antaine

-0.60

Otherwise

-0.59

 else

-0.58

RTLD

-0.58

iterraneo

-0.56

POSITIVE LOGITS

ResponseWriter

0.53

新人

0.52

fastjson

0.50

inSlope

0.50

 forklar

0.49

 bodyParser

0.49

 invokingState

0.48

silia

0.47

 rookie

0.46

ModelAdmin

0.45

Activations Density 5.566%

code syntax such as boolean operators, assignment operators, and parentheses

punctuation

No Comments

No Known Activations