INDEX

Explanations

words related to medicine, education, government, or economics

oai_token-act-pair · gemini-2.0-flash

Formal language

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

Портал

-0.65

PerformLayout

-0.62

enumi

-0.51

 mergeFrom

-0.50

 fût

-0.50

atteindre

-0.48

 fillets

-0.48

 natale

-0.48

 couverts

-0.48

antd

-0.47

POSITIVE LOGITS

 ISNI

0.73

AddTagHelper

0.72

featureID

0.66

 education

0.59

DataAnnotations

0.57

 CGRectMake

0.55

createTextNode

0.54

writeFieldEnd

0.53

 AttributeSet

0.52

 ModelExpression

0.52

Activations Density 3.772%

words related to medicine, education, government, or economics

Formal language

No Comments

No Known Activations