INDEX

Explanations

Russian words, especially in the context of e-commerce

oai_token-act-pair · gemini-2.0-flash

рия

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

########.

-0.77

ukone

-0.71

bootstrapcdn

-0.69

Portály

-0.66

OGND

-0.65

NameInMap

-0.63

Obrázky

-0.62

 Италијани

-0.59

antlr

-0.59

 незавершена

-0.58

POSITIVE LOGITS

 pouvoirs

0.57

 prossima

0.55

 dieux

0.53

 élas

0.52

 télécharge

0.51

 pescoço

0.51

 häl

0.50

 Theſe

0.50

 effray

0.50

 suaminya

0.50

Activations Density 0.592%

Russian words, especially in the context of e-commerce

рия

No Comments

No Known Activations