INDEX

Explanations

references to emergency alerts or public address systems

oai_token-act-pair · gemini-2.0-flash

alerts and public announcements

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Autoritní

-0.58

 tubercle

-0.56

 quæ

-0.56

 Platon

-0.54

 ventral

-0.50

rungsseite

-0.50

 Hopf

-0.49

 webb

-0.49

ovp

-0.49

 weaving

-0.48

POSITIVE LOGITS

BufferException

0.78

MemoryWarning

0.68

PerformLayout

0.59

 '\\;'

0.57

̍t

0.56

 Roskov

0.53

LEncoder

0.52

Parcelize

0.52

announcement

0.51

gameserver

0.51

Activations Density 1.550%

references to emergency alerts or public address systems

alerts and public announcements

No Comments

No Known Activations