© 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-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57221
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0.64
     использования
    0.58
    ema
    0.55
    bara
    0.54
    usha
    0.54
    ya
    0.53
     заключения
    0.52
    p
    0.52
     применения
    0.51
    ;
    0.51
    POSITIVE LOGITS
    ोजन
    0.57
     স্বীক
    0.57
    اي
    0.56
     Colombie
    0.55
     Frum
    0.55
    榖
    0.54
     Hendrix
    0.53
     Jacoby
    0.53
    Colomb
    0.53
    Colombia
    0.53
    Activations Density 0.012%

    No Known Activations