INDEX

Explanations

a variety of code-related terms and symbols

oai_token-act-pair · gemini-2.0-flash

code snippets

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

 systolic

-0.49

 Supremo

-0.49

VIAF

-0.49

↴

-0.49

 perpetuity

-0.47

 GIPHY

-0.47

 crescent

-0.47

 skimage

-0.47

 terci

-0.46

 Melch

-0.46

POSITIVE LOGITS

SharedDtor

0.67

 himo

0.64

iconque

0.64

Personensuche

0.63

 Roskov

0.59

+#+

0.56

OGND

0.56

styleType

0.56

ReusableCell

0.56

TagMode

0.55

Activations Density 0.490%

a variety of code-related terms and symbols

code snippets

No Comments

No Known Activations