INDEX

Explanations

code, numerical data, and words associated with it.

oai_token-act-pair · gemini-2.0-flash

finance and regulations

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

XmlAccessType

-0.84

ukone

-0.67

NewUrlParser

-0.67

 سكانية

-0.65

ArgsConstructor

-0.61

олові

-0.61

 einerseits

-0.59

 мәкалә

-0.59

Rüyada

-0.59

 iconTwitter

-0.59

POSITIVE LOGITS

 onBackPressed

0.47

seeded

0.45

losed

0.42

Viitteet

0.42

 knack

0.41

Ranks

0.41

 Sachs

0.41

UnitTesting

0.41

ArgumentParser

0.41

acen

0.40

Activations Density 4.429%

code, numerical data, and words associated with it.

finance and regulations

No Comments

No Known Activations