INDEX

Explanations

legal language used in court opinions

oai_token-act-pair · gemini-2.0-flash

free speech and law

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

')));

-0.53

 endregion

-0.51

StructEnd

-0.50

 contextLoads

-0.50

")));

-0.49

nextSibling

-0.46

")));

-0.46

spaceBetween

-0.45

}$

-0.44

 BufferedImage

-0.43

POSITIVE LOGITS

CodeAttribute

0.63

 propOrder

0.62

hates

0.57

queryInterface

0.56

MethodManager

0.55

Tē

0.54

setupUi

0.54

Abitanti

0.53

rophobic

0.53

EndProject

0.52

Activations Density 10.226%

legal language used in court opinions

free speech and law

No Comments

No Known Activations