INDEX

Explanations

words related to hygiene and infection

oai_token-act-pair · gemini-2.0-flash

foreign language?

np_token-act-pair-logits · gemini-2.0-flash

disant

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

opel

-0.52

DJANGO

-0.48

EndContext

-0.47

+#+

-0.47

pazität

-0.47

PMailer

-0.46

hdl

-0.45

ModelForm

-0.45

BeginInit

-0.44

rasil

-0.43

POSITIVE LOGITS

 disant

0.56

paravant

0.55

awtextra

0.54

 ainfi

0.54

 mères

0.53

RunWith

0.52

 Banken

0.52

 actualité

0.52

 ſtate

0.49

 myſelf

0.49

Activations Density 4.210%

words related to hygiene and infection

foreign language?

disant

No Comments

No Known Activations