INDEX

Explanations

LaTeX and React code

oai_token-act-pair · gemini-2.0-flash

Code/mathematical notation

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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>

-1.20

CDATA

-0.57

 <>",

-0.55

endregion

-0.54

strijd

-0.54

 Ecke

-0.54

期刊论文

-0.53

 Abend

-0.52

 ISNI

-0.51

(['/

-0.51

POSITIVE LOGITS

 InputDecoration

0.85

protoimpl

0.61

 greateſt

0.60

]='\

0.56

̈́

0.56

enschappelijke

0.54

 dieß

0.52

 beſt

0.52

躇

0.52

NameInMap

0.51

Activations Density 1.935%

LaTeX and React code

Code/mathematical notation

No Comments

No Known Activations