INDEX

Explanations

superscripted numbers and author names in scientific papers.

oai_token-act-pair · gemini-2.0-flash

$^{

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 betweenstory

-0.85

 समीक्षाओं

-0.80

存于互联网档案馆

-0.76

 Aphrodite

-0.66

ReactDOM

-0.65

 Mahomet

-0.61

 bezeichneter

-0.61

ValueStyle

-0.60

msgTypes

-0.60

 ujednoznacz

-0.60

POSITIVE LOGITS

Билгалдахарш

0.71

entierung

0.51

 gainera

0.48

Дереккөздер

0.44

kannt

0.43

MemoryWarning

0.42

viewBox

0.42

enski

0.41

Istorija

0.41

SizeF

0.41

Activations Density 0.224%

superscripted numbers and author names in scientific papers.

$^{

No Comments

No Known Activations