INDEX

Explanations

medical terminology related to diseases and patient conditions

oai_token-act-pair · gemini-2.0-flash

medical texts

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

enumi

-0.73

fromCharCode

-0.66

 Públicas

-0.63

UnusedPrivate

-0.63

 anus

-0.63

 مشين

-0.62

 esternos

-0.60

 Roskov

-0.60

Билгалдахарш

-0.59

 kaarangay

-0.58

POSITIVE LOGITS

 high

0.49

av

0.47

getMinutes

0.44

 '').

0.43

 true

0.42

 functional

0.41

 hyper

0.40

))/(

0.40

origine

0.39

=""/>

0.39

Activations Density 3.691%

medical terminology related to diseases and patient conditions

medical texts

No Comments

No Known Activations