INDEX

Explanations

customer testimonials and reviews.

oai_token-act-pair · gemini-2.0-flash

period

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

IsInitialized

-0.59

Czytaj

-0.56

 initComponents

-0.53

 Hippo

-0.53

NameValuePair

-0.52

tws

-0.51

 Heav

-0.51

 papyrus

-0.51

 Puis

-0.50

lossary

-0.49

POSITIVE LOGITS

 From

0.62

From

0.56

mybatisplus

0.53

XmlType

0.51

 endforeach

0.49

стюм

0.48

gaard

0.47

DATABASES

0.47

 whether

0.46

 FROM

0.46

Activations Density 11.251%

customer testimonials and reviews.

period

No Comments

No Known Activations