INDEX

Explanations

legal and regulatory language and terms

oai_token-act-pair · gemini-2.0-flash

Legal statutes

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 للمعارف

-0.59

 ProtoMessage

-0.54

parsedMessage

-0.53

>>;

-0.52

 Legislation

-0.51

 betweenstory

-0.49

 <<<<<<<<<<<<<<

-0.49

 ?>">

-0.49

withIdentifier

-0.48

 legislation

-0.48

POSITIVE LOGITS

醐

0.52

rschein

0.51

 Gump

0.50

 lays

0.48

 knap

0.47

 Closes

0.46

 intptr

0.46

 closing

0.46

 address

0.46

handle

0.46

Activations Density 5.958%

legal and regulatory language and terms

Legal statutes

No Comments

No Known Activations