INDEX

Explanations

words related to lab procedures with blood or other biological samples

oai_token-act-pair · gemini-2.0-flash

Scientific assay context

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

Personendaten

-0.64

 autorytatywna

-0.59

webElementXpaths

-0.59

 BrowserModule

-0.53

,:);

-0.52

=="")

-0.52

ChildScrollView

-0.51

webElement

-0.50

rungsseite

-0.50

 defaultstate

-0.50

POSITIVE LOGITS

 sintering

0.57

tvguidetime

0.56

 implants

0.53

 riego

0.52

 inhibitors

0.52

piram

0.51

 lusso

0.51

 stenosis

0.51

 dryers

0.49

 activations

0.49

Activations Density 22.885%

words related to lab procedures with blood or other biological samples

Scientific assay context

No Comments

No Known Activations