INDEX

Explanations

words related to legal and regulatory language about required behavior

oai_token-act-pair · gemini-2.0-flash

Legal/technical documents

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 Biôgrafia

-0.66

homonymie

-0.66

KommentareTeilen

-0.64

<bos>

-0.62

BASEPATH

-0.60

Autoritní

-0.60

出版年

-0.54

ThroughAttribute

-0.54

قایناق‌لار

-0.53

POSITIVE LOGITS

0.93

endphp

0.55

 tartalomajánló

0.49

 AttributeSet

0.49

 vectorielles

0.47

 кӀош

0.46

 препратки

0.46

 useContext

0.44

seamnă

0.44

endpush

0.44

Activations Density 1.811%

words related to legal and regulatory language about required behavior

Legal/technical documents

No Comments

No Known Activations