INDEX

Explanations

the word "well" and words appearing near it

oai_token-act-pair · gemini-2.0-flash

well

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 ligiloj

-0.68

 initComponents

-0.67

TagMode

-0.66

 BorderSide

-0.63

ChildScrollView

-0.60

 Италијани

-0.60

BoxShadow

-0.59

 nakalista

-0.58

endphp

-0.57

 itſelf

-0.56

POSITIVE LOGITS

 (!__

0.56

 most

0.52

bump

0.51

ositol

0.51

erez

0.50

 Road

0.50

 compare

0.49

culata

0.49

Der

0.48

bú

0.48

Activations Density 2.113%

the word "well" and words appearing near it

well

No Known Activations