INDEX

Explanations

language related to medical imaging and diagnostics, especially descriptions of lesions.

oai_token-act-pair · gemini-2.0-flash

technical or medical terminology related to imaging

np_token-act-pair-logits · gpt-4o-mini

Medical imaging, tumors

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aarrggbb

-0.53

invokeLater

-0.49

ellite

-0.48

 Properties

-0.48

antMatchers

-0.44

Multivariate

-0.43

seled

-0.42

katy

-0.42

 retour

-0.42

alysis

-0.42

POSITIVE LOGITS

ThroughAttribute

0.76

lccn

0.61

richTextPanel

0.57

makeText

0.52

FTFY

0.51

 typelib

0.50

 freund

0.49

multer

0.49

zzleHttp

0.49

)_/¯

0.48

Activations Density 3.815%

language related to medical imaging and diagnostics, especially descriptions of lesions.

technical or medical terminology related to imaging

Medical imaging, tumors

No Comments

No Known Activations