INDEX

Explanations

words related to medical studies and patient assessment

oai_token-act-pair · gemini-2.0-flash

medical assessments

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

addington

-0.56

 linkovi

-0.55

ugier

-0.54

 OMITBAD

-0.54

 StatelessWidget

-0.53

出版年

-0.52

yonel

-0.52

arschu

-0.51

 kasarigan

-0.50

 Signalez

-0.50

POSITIVE LOGITS

tut

0.54

ιώ

0.50

::-

0.48

rien

0.47

 ISBN

0.46

ViewFeatures

0.45

asn

0.45

 inhale

0.45

ISBN

0.44

AddTagHelper

0.44

Activations Density 26.432%

words related to medical studies and patient assessment

medical assessments

No Comments

No Known Activations