INDEX

Explanations

mathematical equations and notation

oai_token-act-pair · gemini-2.0-flash

algebraic geometry

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 BorderSide

-0.58

 للمعارف

-0.56

EndProject

-0.53

 actionMode

-0.51

eningrad

-0.51

mpä

-0.50

Введение

-0.50

?}",

-0.50

 Blackout

-0.49

älte

-0.49

POSITIVE LOGITS

بوابة

0.58

enumi

0.54



0.51

findpost

0.50

Abp

0.49

expandindo

0.46

 gjerne

0.44

 Caledonia

0.44

 هن

0.44

scriptId

0.43

Activations Density 2.627%

mathematical equations and notation

algebraic geometry

No Comments

No Known Activations