INDEX

Explanations

dates and short related words

oai_token-act-pair · gemini-2.0-flash

Months

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

ThemeOverlay

-0.79

 Bioaccumulative

-0.72

 setae

-0.69

 createState

-0.65

ьаж

-0.65

новниш

-0.65

 Njema

-0.64

ształ

-0.64

VideoCapture

-0.64

LookAnd

-0.62

POSITIVE LOGITS

󠁢

0.62

urb

0.53

mart

0.51

urf

0.51

buro

0.51

enberg

0.50

orp

0.49

phere

0.48

pell

0.47

urbs

0.47

Activations Density 12.021%

dates and short related words

Months

No Comments

No Known Activations