INDEX

Explanations

medical terminology and valedictions in both English and French

oai_token-act-pair · gemini-2.0-flash

Aiheesta

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

 autorytatywna

-0.60

SizeF

-0.55

principalColumn

-0.54

#+#

-0.54

 onOptions

-0.51

Espèce

-0.49

 viewType

-0.48

 BrowserModule

-0.47

روس

-0.46

lateur

-0.46

POSITIVE LOGITS

Aiheesta

0.56

IANI

0.52

󠁿

0.52

EDEFAULT

0.51

くなりました

0.51

ұл

0.49

htë

0.48

ZIE

0.47

 State

0.47

yaitu

0.47

Activations Density 0.154%

medical terminology and valedictions in both English and French

Aiheesta

No Comments

No Known Activations