INDEX

Explanations

the idioms "taken by surprise" and "caught off guard."

oai_token-act-pair · gemini-2.0-flash

caught

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 resourceCulture

-0.86

StoryboardSegue

-0.77

tagHelperRunner

-0.71

RegistryLite

-0.68

expandindo

-0.67

 незавершена

-0.66

OrNil

-0.65

IsContent

-0.61

 ProtoMessage

-0.60

 estekak

-0.58

POSITIVE LOGITS

off

0.56

 froide

0.51

 Fanning

0.50

 dorada

0.48

OFF

0.46

PWD

0.46

 rød

0.46

chappement

0.46

הערות

0.45

 elettron

0.44

Activations Density 0.618%

the idioms "taken by surprise" and "caught off guard."

caught

No Comments

No Known Activations