INDEX

Explanations

the "organis(z)ation" and similar words.

oai_token-act-pair · gemini-2.0-flash

organization

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 مرئيه

-0.75

sune

-0.61

 Monfieur

-0.60

VersionUID

-0.58

 déput

-0.57

ufnahme

-0.57

IBarButtonItem

-0.56

PasswordField

-0.56

 présidenti

-0.56

 Paix

-0.55

POSITIVE LOGITS

 Organization

0.90

 Organ

0.89

 organis

0.87

 organization

0.86

organ

0.86

 ORGAN

0.85

 Organisation

0.84

Organ

0.82

 organisation

0.82

 organiz

0.81

Activations Density 1.147%

the "organis(z)ation" and similar words.

organization

No Comments

No Known Activations