INDEX

Explanations

text marked up with html-ish tags and/or citation references

oai_token-act-pair · gemini-2.0-flash

0

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

</caption>

-0.70

__(/*!

-0.53

 AppColors

-0.50

 Theſe

-0.49

 Monfieur

-0.49

Efq

-0.48

-0.47

%]

-0.47

 المعيارى

-0.45

 Watcher

-0.45

POSITIVE LOGITS

 LUMP

0.62

0.57

 makeStyles

0.57

 externi

0.56

0.55

tvguidetime

0.54

yii

0.52

WebElementEntity

0.50

Бахар

0.50

Activations Density 2.426%

text marked up with html-ish tags and/or citation references

0

No Comments

No Known Activations