INDEX

Explanations

mentions of drug use

oai_token-act-pair · gemini-2.0-flash

drug

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

IsContent

-0.50

KommentareTeilen

-0.47

 trän

-0.44

 profundos

-0.44

httphttps

-0.44

 brugt

-0.43

 hänen

-0.42

 vuoden

-0.41

 muligt

-0.41

 chilling

-0.41

POSITIVE LOGITS

enterOuterAlt

0.78

AsUp

0.69

 <=",

0.64

 تضيفلها

0.64

Geplaatst

0.63

 ExecuteAsync

0.63

ьаж

0.62

 ffilmiau

0.61

 pinulongan

0.61

ChildScrollView

0.60

Activations Density 1.423%

mentions of drug use

drug

No Comments

No Known Activations