INDEX

Explanations

words relating to manufactured inanimant objects and the places where they are found

oai_token-act-pair · gemini-2.0-flash

Places and organizations

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

amaño

-0.65

 skola

-0.63

anzug

-0.62

veyard

-0.62

erschrank

-0.60

antiation

-0.59

vaders

-0.59

 LIRE

-0.58

 кабинет

-0.58

üstung

-0.57

POSITIVE LOGITS

UnusedPrivate

0.64

帖最后由

0.59

 disambiguazione

0.58

GraphicsUnit

0.52

sidemargin

0.52

TableHead

0.51

 AssemblyCompany

0.51

 EdgeInsets

0.50

writeFieldEnd

0.50

oneofs

0.49

Activations Density 2.227%

words relating to manufactured inanimant objects and the places where they are found

Places and organizations

No Comments

No Known Activations