INDEX

Explanations

blocks of code

oai_token-act-pair · gemini-2.0-flash

code snippets

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 snippetHide

-0.69

styleType

-0.68

UnusedPrivate

-0.67

PhysRevLett

-0.65

 onPostExecute

-0.63

Xna

-0.63

InputBorder

-0.63

prefixer

-0.62

 ModelExpression

-0.62

disposing

-0.61

POSITIVE LOGITS

zyw

0.41

ArgsConstructor

0.39

omores

0.38

jej

0.37

roned

0.36

ikt

0.35

+:+

0.35

 NSCoder

0.34

iann

0.34

=====

0.34

Activations Density 2.687%

blocks of code

code snippets

No Comments

No Known Activations