INDEX

Explanations

descriptions of violent physical conflict and its setup.

oai_token-act-pair · gemini-2.0-flash

ground/floor

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

RectangleBorder

-0.77

 تانيه

-0.77

 vuitton

-0.70

yntaxException

-0.63

 ujednoznacz

-0.60

RTDA

-0.59

Serviço

-0.59

 cref

-0.58

 RouterModule

-0.56

 correctes

-0.56

POSITIVE LOGITS

 ground

1.96

ground

1.74

 floor

1.67

Ground

1.66

 Ground

1.59

 GROUND

1.50

floor

1.45

 Floor

1.41

GROUND

1.39

Floor

1.38

Activations Density 0.590%

descriptions of violent physical conflict and its setup.

ground/floor

No Comments

No Known Activations