INDEX

Explanations

mentions of departments and centers within institutions

oai_token-act-pair · gemini-2.0-flash

foreign words

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

throw

-0.44

 throws

-0.42

zit

-0.41

函

-0.40

pyx

-0.39

 stew

-0.38

indre

-0.37

tags

-0.37

 threw

-0.36

Pyx

-0.35

POSITIVE LOGITS

 Diſ

0.76

 enfans

0.74

Autoritní

0.71

 Chriftian

0.71

 autorytatywna

0.71

 normaux

0.70

 démocr

0.70

Eſ

0.69

 ſeveral

0.69

 ſtate

0.68

Activations Density 3.860%

mentions of departments and centers within institutions

foreign words

No Comments

No Known Activations