INDEX

Explanations

medical facilities and hospitals, especially ones connected to the NHS

oai_token-act-pair · gemini-2.0-flash

Hospitals and medical practices

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

MemoryWarning

-0.83

 propOrder

-0.83

 EconPapers

-0.82

 Réponses

-0.80

StoryboardSegue

-0.80

 betweenstory

-0.77

 NSCoder

-0.75

 resourceCulture

-0.73

انيف

-0.73

 '\\;'

-0.71

POSITIVE LOGITS

ⓘ

0.62

pai

0.46

major

0.43

 poko

0.43

 Foer

0.42

 सक

0.42

泸

0.42

RunWith

0.41

innen

0.41

 Lumpur

0.41

Activations Density 0.296%

medical facilities and hospitals, especially ones connected to the NHS

Hospitals and medical practices

No Comments

No Known Activations