INDEX

Explanations

the name "Kar" and similar names

oai_token-act-pair · gemini-2.0-flash

kar

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

 Bioaccumulative

-0.73

NameInMap

-0.72

__(/*!

-0.70

GEBURTSDATUM

-0.65

पया

-0.65

Géographie

-0.65

UnusedPrivate

-0.63

<?

-0.61

esModule

-0.61

UserScript

-0.60

POSITIVE LOGITS

 épais

0.46

omena

0.45

KommentareTeilen

0.43

 poffible

0.41

imov

0.41

onload

0.40

Cubit

0.40

 sauvages

0.39

Zug

0.39

stum

0.39

Activations Density 0.576%

the name "Kar" and similar names

kar

No Comments

No Known Activations