INDEX

Explanations

words related to medical/pharmaceutical topics, particularly clinical trials and studies, regulatory approvals, and commercialization

oai_token-act-pair · gemini-2.0-flash

clinical

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

-2.20

 Clinical

-2.09

clinical

-2.03

Clinical

-2.02

 CLINICAL

-1.89

CLINICAL

-1.70

 Clin

-1.64

 clinically

-1.56

 clinique

-1.48

 clínica

-1.47

POSITIVE LOGITS

nocache

0.53

ViewImports

0.52

GEBURTSDATUM

0.51

fortawesome

0.48

PREFERRED

0.48

leria

0.47

леге

0.47

endront

0.46

ElementException

0.45

 kraf

0.45

Activations Density 1.495%

words related to medical/pharmaceutical topics, particularly clinical trials and studies, regulatory approvals, and commercialization

clinical

No Comments

No Known Activations