INDEX

Explanations

code-related markup and comments

oai_token-act-pair · gemini-2.0-flash

code delimiters

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

<bos>

-0.63

ISupport

-0.58

 himo

-0.52

 jsPsych

-0.50

 mouseY

-0.49

StoryboardSegue

-0.48

jss

-0.47

+:+

-0.46

lou

-0.46

RUnlock

-0.45

POSITIVE LOGITS

ⓧ

0.54

kolwiek

0.46

viewDidLoad

0.40

ButterKnife

0.39

violi

0.39

reportWebVitals

0.39

enius

0.39

MemoryWarning

0.38

 textStatus

0.38

AndEndTag

0.38

Activations Density 1.121%

code-related markup and comments

code delimiters

No Comments

No Known Activations