INDEX

Explanations

HTML code, especially related to scheduling and displaying content

oai_token-act-pair · gemini-2.0-flash

HTML formatting tags

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

Negative Logits

تقاوى

-0.90

دانشنامهٔ

-0.65

 tartalomajánló

-0.63

BeginContext

-0.61

￡

-0.60

 initComponents

-0.59

 Paglinawan

-0.59

Identyfik

-0.57

ukunft

-0.56

titleMargin

-0.56

POSITIVE LOGITS

ASTIC

0.54

 mergeFrom

0.53

koord

0.48

 useSelector

0.48

TabStop

0.48

owohl

0.47

TextWatcher

0.47

 ViewGroup

0.47

...

0.46

 Vortex

0.46

Activations Density 38.817%

HTML code, especially related to scheduling and displaying content

HTML formatting tags

No Known Activations