INDEX

Explanations

phrases involving war or competition

oai_token-act-pair · gemini-2.0-flash

winning

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

:^(

-0.53

 AttributeSet

-0.52

elfs

-0.51

resizingMask

-0.50

UIControlState

-0.49

сни

-0.48

DebuggerNonUser

-0.47

 VIAF

-0.47

theim

-0.47

excess

-0.46

POSITIVE LOGITS

win

0.79

win

0.73

addCriterion

0.70

 выигра

0.69

Win

0.66

 remporté

0.65

 vinto

0.65

 wins

0.64

 winning

0.64

Win

0.64

Activations Density 1.290%

phrases involving war or competition

winning

No Comments

No Known Activations