INDEX

Explanations

discussion of medical conditions and procedures, often in the context of diagnosis, treatment, and symptoms

oai_token-act-pair · gemini-2.0-flash

Diseases and medical conditions

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

antaranya

-0.72

berdayakan

-0.63

 cerimonia

-0.60

 onderhoud

-0.59

 commerciales

-0.59

 spéciaux

-0.59

 tiegħek

-0.57

 stället

-0.56

 piattaforma

-0.56

umumkan

-0.56

POSITIVE LOGITS

 defaultstate

0.69

 cancer

0.66

 metastasis

0.63

 pain

0.61

 nerve

0.60

 scar

0.59

 schizophrenia

0.55

 sores

0.54

 meningitis

0.54

 blindness

0.54

Activations Density 18.818%

discussion of medical conditions and procedures, often in the context of diagnosis, treatment, and symptoms

Diseases and medical conditions

No Comments

No Known Activations