INDEX

Explanations

statistical analysis and scientific modeling

oai_token-act-pair · gemini-2.0-flash

Perfect, pure, ideal

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

 bezeichneter

-0.86

RectangleBorder

-0.79

 jScrollPane

-0.75

 ddelweddau

-0.68

 itſelf

-0.67

 سكانية

-0.66

 contextLoads

-0.66

Autoritní

-0.65

 ―――――

-0.64

 chofe

-0.64

POSITIVE LOGITS

 perfect

1.08

 Perfect

0.86

perfect

0.82

Perfect

0.81

 pure

0.75

 perfectly

0.75

 PERFECT

0.75

 free

0.75

 ideal

0.74

 zero

0.70

Activations Density 5.114%

statistical analysis and scientific modeling

Perfect, pure, ideal

No Comments

No Known Activations