INDEX

Explanations

capital letters followed or preceded by connecting characters, plus groups of related capital letters

oai_token-act-pair · gemini-2.0-flash

Code/Math Snippets

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

igil

-0.54

XmlSchema

-0.48

<bos>

-0.47

Der

-0.44

Wel

-0.43

toPromise

-0.43

ragona

-0.42

Res

-0.42

 Proof

-0.41

теристи

-0.41

POSITIVE LOGITS

 Majefty

0.75

RenderAtEndOf

0.70

 مرئيه

0.70

 ifrån

0.68

RTEX

0.67

antaranya

0.66

 ujednoznacz

0.66

Hochspringen

0.65

 Theſe

0.65

دانشنامهٔ

0.65

Activations Density 1.804%

capital letters followed or preceded by connecting characters, plus groups of related capital letters

Code/Math Snippets

No Comments

No Known Activations