INDEX

Explanations

terms related to government, politics, and education jobs

oai_token-act-pair · gemini-2.0-flash

holding a position

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

 Lightboxes

-0.49

Initializable

-0.47

kháu

-0.45

 výkon

-0.44

 Übergang

-0.44

AlterField

-0.42

NoSuchAlgorithm

-0.42

 bağlantılar

-0.41

 recevrez

-0.41

 gente

-0.40

POSITIVE LOGITS

 ModelExpression

0.69

tagHelperRunner

0.66

 surla

0.62

]--;

0.61

 PublicKey

0.60

∛

0.57

PhysRevD

0.56

setVerticalGroup

0.55

 pinulongan

0.53

┛

0.53

Activations Density 24.056%

terms related to government, politics, and education jobs

holding a position

No Comments

No Known Activations