INDEX

Explanations

mentions of numbers, especially quantities of time

oai_token-act-pair · gemini-2.0-flash

Numbers

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

 succulent

-0.56

TALL

-0.52

ΕΣ

-0.50

术

-0.50

ibig

-0.49

łk

-0.48

ริม

-0.48

 Merlin

-0.48

動

-0.48

 Toch

-0.48

POSITIVE LOGITS

addContainerGap

0.57

0.54

XmlAccessorType

0.54

WQS

0.53

الإنجليزية

0.53

̅

0.53

])):

0.52

"}>

0.52

'}';

0.52

šanās

0.52

Activations Density 6.867%

mentions of numbers, especially quantities of time

Numbers

No Comments

No Known Activations