INDEX

Explanations

content related to radio or electromagnetic interference, radiation, or signals

oai_token-act-pair · gemini-2.0-flash

electromagnetic

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

-0.48

<bos>

-0.44

zeichnungen

-0.43

}{}

-0.42

]}{

-0.42

Am

-0.41

Documented

-0.41

-0.40

POSITIVE LOGITS

 متعلقه

0.78

 ModelExpression

0.71

 chré

0.71

 صوتيه

0.70

esez

0.70

はじめに

0.69

 esternos

0.68

 dépens

0.68

EndGlobalSection

0.65

 vectorielles

0.63

Activations Density 1.028%

content related to radio or electromagnetic interference, radiation, or signals

electromagnetic

No Comments

No Known Activations