INDEX

Explanations

words related to politics, legal systems, and organizations

oai_token-act-pair · gemini-2.0-flash

organizations

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

 AssemblyCulture

-1.06

RenderAtEndOf

-1.00

 itſelf

-0.85

 myſelf

-0.83

 iſt

-0.78

ynchronously

-0.76

 Catawiki

-0.73

TextWatcher

-0.71

 doubtnut

-0.71

ſelves

-0.69

POSITIVE LOGITS

’

0.66

0.64

0.46

‘

0.39

′

0.39

ⓘ

0.39

that

0.38

XmlAccessType

0.37

望

0.37

ˈ

0.36

Activations Density 2.972%

words related to politics, legal systems, and organizations

organizations

No Comments

No Known Activations