INDEX

Explanations

Russian language code and expressions

oai_token-act-pair · gemini-2.0-flash

multilingual quotes and code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

SourceChecksum

-0.78

 سكانية

-0.77

IndentedString

-0.77

ьаж

-0.76

 defaultstate

-0.75

ValueStyle

-0.74

AsUp

-0.74

contentLoaded

-0.74

migrationBuilder

-0.73

 ostavi

-0.73

POSITIVE LOGITS

 Francesco

0.53

 Christoph

0.53

 François

0.52

 Carmine

0.51

 Domenico

0.50

 Francois

0.50

 Vasily

0.49

 Nadal

0.49

cach

0.48

 Алексей

0.47

Activations Density 0.833%

Russian language code and expressions

multilingual quotes and code

No Comments

No Known Activations