INDEX

Explanations

words that have to do with arrangements, trust, or obligation

oai_token-act-pair · gemini-2.0-flash

place

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

'])){

-0.63

 SwitchCompat

-0.61

zuführen

-0.49

'){

-0.49

)__

-0.49

Datuak

-0.48

thisis

-0.47

':

-0.46

']))

-0.45

 calldata

-0.43

POSITIVE LOGITS

RenderAtEndOf

0.65

awtextra

0.61

fml

0.60

ьаж

0.56

 Biôgrafia

0.54

 børn

0.54

ItemBackground

0.53

marshaller

0.52

 chi̍t

0.52

 blanches

0.52

Activations Density 10.275%

words that have to do with arrangements, trust, or obligation

place

No Comments

No Known Activations