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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12393
    Prev
    Next
    INDEX
    Explanations

    words related to the Hindu religion, specifically the deity Lord Narasimha.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    RUnlock
    -0.67
    ReusableCell
    -0.66
     Италијани
    -0.65
    
    -0.62
     disambiguazione
    -0.62
    GEBURTSDATUM
    -0.60
    isContained
    -0.59
    Xna
    -0.59
     AssemblyProduct
    -0.59
    parsedMessage
    -0.57
    POSITIVE LOGITS
    empereur
    0.56
     teatr
    0.49
     teater
    0.49
    MATRIX
    0.49
     regulated
    0.47
    évêque
    0.46
     K
    0.46
     symptômes
    0.45
    ｀*)
    0.45
     Kuchen
    0.45
    Activations Density 1.179%

    No Known Activations