INDEX

Explanations

descriptions of the features of physical products.

oai_token-act-pair · gemini-2.0-flash

technical components

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

parsedMessage

-0.52

Населення

-0.47

 allAfrica

-0.44

 CanadaChoose

-0.43

findpost

-0.42

Ethnicity

-0.42

 correlations

-0.41

 Representing

-0.40

 Committees

-0.40

 Seligman

-0.40

POSITIVE LOGITS

 Piston

0.66

 Battery

0.64

Battery

0.62

Dishwasher

0.62

Brake

0.59

 Tank

0.57

Knife

0.57

 Cable

0.57

Weld

0.56

 Brush

0.56

Activations Density 25.455%

descriptions of the features of physical products.

technical components

No Comments

No Known Activations