INDEX

Explanations

career and position titles, especially in academia.

oai_token-act-pair · gemini-2.0-flash

Biography or description of people

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

fromnode

-1.01

yntaxException

-0.98

 <>",

-0.91

 GenerationType

-0.90

 AssemblyCompany

-0.82

IsMutable

-0.82

saraba

-0.77

,:);

-0.76

SBATCH

-0.76

 تضيفلها

-0.73

POSITIVE LOGITS

section

0.42

tert

0.39

 disposición

0.39

je

0.39

joy

0.38

 nazionali

0.38

 bianche

0.37

Po

0.37

 happy

0.36

UMEN

0.35

Activations Density 0.763%

career and position titles, especially in academia.

Biography or description of people

No Comments

No Known Activations