INDEX

Explanations

mathematical equations and derivatives

oai_token-act-pair · gemini-2.0-flash

Initial

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

Negative Logits

 مشين

-0.81

ništ

-0.72

 Administrativna

-0.71

 متعلقه

-0.69

XmlEnum

-0.68

 Audiodateien

-0.66

ècie

-0.65

 AssemblyTitle

-0.61

sements

-0.59

ⓧ

-0.59

POSITIVE LOGITS

Initial

0.70

 Initial

0.70

initial

0.67

 initial

0.66

 INITIAL

0.65

 initialize

0.63

INITIAL

0.60

 initi

0.60

initi

0.59

initialize

0.59

Activations Density 1.563%

mathematical equations and derivatives

Initial

No Known Activations