INDEX

Explanations

numerical values separated by commas

oai_token-act-pair · gemini-2.0-flash

comma

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

postmedia

-0.42

ary

-0.35

KATH

-0.31

And

-0.30

interopRequire

-0.29

ent

-0.29

mstyle

-0.29

of

-0.29

al

-0.27

mt

-0.27

POSITIVE LOGITS

 AssemblyCompany

0.91

 myſelf

0.87

RectangleBorder

0.85

 ―――――

0.84

CloseOperation

0.84

 فريبيس

0.84

Efq

0.83

ftagPool

0.81

ſelf

0.80

ſelves

0.80

Activations Density 1.862%

numerical values separated by commas

comma

No Comments

No Known Activations