INDEX

Explanations

occurrences of the word "create" along with words that come just before or after "create"

oai_token-act-pair · gemini-2.0-flash

create

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

ungsver

-0.52

 Amount

-0.52

 tabPage

-0.52

 perna

-0.51

henge

-0.49

 Carbide

-0.48

 creciendo

-0.48

tito

-0.46

idencias

-0.45

 AMOUNT

-0.44

POSITIVE LOGITS

ReusableCell

0.81

WireFormatLite

0.73

Geplaatst

0.66

MemoryWarning

0.65

 protoimpl

0.65

richTextPanel

0.63

withIdentifier

0.62

NameInMap

0.59

tagext

0.59

FailureListener

0.58

Activations Density 2.708%

occurrences of the word "create" along with words that come just before or after "create"

create

No Comments

No Known Activations