INDEX

Explanations

articles (a, an, the) preceding nouns, especially when associated with dates, inventions, or items.

oai_token-act-pair · gemini-2.0-flash

definitions and descriptions

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 või

-0.51

 africains

-0.49

Odkazy

-0.48

 fourrure

-0.47

 spéciales

-0.47

or

-0.46

 اینترنتی

-0.46

läge

-0.45

 egens

-0.45

 aéri

-0.44

POSITIVE LOGITS

Personensuche

1.09

دانشنامهٔ

0.76

 autorytatywna

0.75

aarrggbb

0.73

 للاسماء

0.68

ⓧ

0.68

AccessorTable

0.68

hyrchwyd

0.65

webElementXpaths

0.64

]='\

0.64

Activations Density 1.622%

articles (a, an, the) preceding nouns, especially when associated with dates, inventions, or items.

definitions and descriptions

No Comments

No Known Activations