INDEX

Explanations

references to property, primarily residences, and legal/financial context related to them.

oai_token-act-pair · gemini-2.0-flash

Residences

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

ContextHolder

-0.52

 para

-0.47

 कोशिश

-0.43

 ок

-0.41

mauer

-0.41

ťou

-0.41

apimachinery

-0.41

bouncycastle

-0.40

ERATION

-0.40

formis

-0.40

POSITIVE LOGITS

 headquarters

0.94

 residence

0.94

 domicile

0.88

 homes

0.84

 residences

0.82

 premises

0.82

 abode

0.78

 offices

0.78

@"/

0.75

QMetaType

0.75

Activations Density 1.472%

references to property, primarily residences, and legal/financial context related to them.

Residences

No Comments

No Known Activations