INDEX

Explanations

legal and criminal justice terminology, especially related to evidence and testing

oai_token-act-pair · gemini-2.0-flash

testing and analysis

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

-0.59

MeasureSpec

-0.52

 kể

-0.49

 altrett

-0.49

(['/

-0.46

 suffit

-0.45

)++;

-0.44

민

-0.43

++);

-0.42

={`/

-0.42

POSITIVE LOGITS

<bos>

0.86

 المعيارى

0.61

vode

0.60

Geplaatst

0.60

 Infórmanos

0.60

structors

0.59

 dispensation

0.57

uque

0.57

 estekak

0.56

Välislingid

0.56

Activations Density 3.208%

legal and criminal justice terminology, especially related to evidence and testing

testing and analysis

No Known Activations