INDEX

Explanations

a combination of abbreviations, numbers, and lab jargon

oai_token-act-pair · gemini-2.0-flash

Technical documentation/scientific papers

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

LQ

-0.69

RG

-0.69

 igång

-0.69

HF

-0.68

PN

-0.68

MF

-0.68

SB

-0.67

RC

-0.67

HG

-0.66

CS

-0.66

POSITIVE LOGITS

MemoryWarning

0.48

jspx

0.48

]),

0.45

 mund

0.43

 esper

0.42

BeginInit

0.42

ged

0.41

"]);

0.40

 Eink

0.40

asgi

0.40

Activations Density 2.583%

a combination of abbreviations, numbers, and lab jargon

Technical documentation/scientific papers

No Comments

No Known Activations