INDEX

Explanations

the word "pre" followed by a hyphen

oai_token-act-pair · gemini-2.0-flash

pre

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 Roskov

-0.49

例文帳に追加

-0.49

详细信息

-0.48

 endwhile

-0.48

=$?

-0.47

xase

-0.47

endpush

-0.46

 Ache

-0.46

 cherchés

-0.45

 متعلقه

-0.45

POSITIVE LOGITS

AxisAlignment

0.56

AsUp

0.52

 rapides

0.52

 retenir

0.52

BASELINE

0.51

ppelin

0.51

transQ

0.50

ITZ

0.50

itz

0.50

 confiança

0.49

Activations Density 0.522%

the word "pre" followed by a hyphen

pre

No Comments

No Known Activations