INDEX

Explanations

words or phrases related to the medical industry or to health in general

oai_token-act-pair · gemini-2.0-flash

medical contexts

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 clinical

-1.57

 clinically

-1.47

 Clinical

-1.44

Clinical

-1.42

clinical

-1.40

 patients

-1.32

 Patients

-1.23

 CLINICAL

-1.23

patient

-1.20

Patients

-1.20

POSITIVE LOGITS

tvguidetime

0.72

UrlResolution

0.68

Personendaten

0.68

ImageContext

0.68

 AssemblyTitle

0.66

MD

0.65

MD

0.63

Md

0.61

Md

0.60

 snippetHide

0.60

Activations Density 5.185%

words or phrases related to the medical industry or to health in general

medical contexts

No Comments

No Known Activations