INDEX

Explanations

the prefix "bra" within words

oai_token-act-pair · gemini-2.0-flash

bra

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

 betweenstory

-0.72

IsContent

-0.62

 насеље

-0.57

huana

-0.54

ariously

-0.54

 kasarigan

-0.52

enumii

-0.52

 Rohr

-0.51

addGap

-0.51

 Both

-0.50

POSITIVE LOGITS

EnableWeb

0.56

 Wikispecies

0.55

AGB

0.54

 kaynağından

0.52

msgTypes

0.49

 niedersachsen

0.47

DbHelper

0.47

 actionMode

0.47

 cref

0.46

 XCTest

0.46

Activations Density 0.148%

the prefix "bra" within words

bra

No Comments

No Known Activations