INDEX

Explanations

code-related text, including syntax and automatically generated content or code.

oai_token-act-pair · gemini-2.0-flash

code and configuration files

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 controllare

-0.51

 endwhile

-0.51

 perche

-0.50

createNewFile

-0.49

 péri

-0.48

bewerken

-0.46

vers

-0.46

 artikkeli

-0.46

 gevolg

-0.45

 Twelfth

-0.44

POSITIVE LOGITS

 חיצוניים

0.66

queryInterface

0.61

 initComponents

0.58

 الأك

0.50

PerformLayout

0.50

таратура

0.50

lapsingToolbar

0.49

ChildIndex

0.48

 lược

0.48

Uri

0.48

Activations Density 0.393%

code-related text, including syntax and automatically generated content or code.

code and configuration files

No Comments

No Known Activations