© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13343
    Prev
    Next
    INDEX
    Explanations

    mentions of markets, especially in a historical context

    oai_token-act-pair · gemini-2.0-flash

    square

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.59
    numerusform
    -0.57
     дописавши
    -0.56
     Projektu
    -0.52
     دیکھیے
    -0.48
    onoi
    -0.45
    脚注の使い方
    -0.44
     disambiguazione
    -0.44
    canestro
    -0.44
    ありが
    -0.44
    POSITIVE LOGITS
     square
    1.02
     squares
    0.90
     Square
    0.83
     piazza
    0.75
     SQUARE
    0.75
    square
    0.75
     beginnetje
    0.72
     station
    0.71
    Square
    0.70
     Piazza
    0.68
    Activations Density 0.928%

    No Known Activations