INDEX

Explanations

technical documentation about medical imaging devices and procedures that use radiation

oai_token-act-pair · gemini-2.0-flash

Radiation

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

setVerticalGroup

-0.63

transQ

-0.62

endpush

-0.59

AppMethodBeat

-0.58

Життєпис

-0.58

quelize

-0.58

principalTable

-0.58

 Económica

-0.58

AutoScale

-0.57

 Memoriam

-0.56

POSITIVE LOGITS

Rad

0.81

Rad

0.76

 dose

0.75

 radiation

0.75

rad

0.74

 Radi

0.69

 radi

0.69

dose

0.68

RAD

0.68

Radiation

0.67

Activations Density 1.763%

technical documentation about medical imaging devices and procedures that use radiation

Radiation

No Comments

No Known Activations