INDEX

Explanations

mentions of doses, percentages, lineages, and injection in scientific studies

oai_token-act-pair · gemini-2.0-flash

vaccinations

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Mota

-0.59

catore

-0.54

Stand

-0.54

chnet

-0.50

kì

-0.49

 KeyError

-0.47

velg

-0.47

ʲ

-0.46

zzato

-0.46

ticia

-0.45

POSITIVE LOGITS

 שוליים

0.70

principalColumn

0.68

Gambas

0.67

 ModelExpression

0.65

ClientSize

0.64

setVerticalGroup

0.63

 jsPsych

0.57

Personendaten

0.57

EndContext

0.57

AxisAlignment

0.57

Activations Density 2.983%

mentions of doses, percentages, lineages, and injection in scientific studies

vaccinations

No Comments

No Known Activations