© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50998
    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_10_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
     an
    0.61
     beho
    0.57
    ）；
    0.55
     嗯
    0.55
    тинг
    0.54
     отмети
    0.54
     proposito
    0.54
     encontramos
    0.53
     arma
    0.53
     ligero
    0.53
    POSITIVE LOGITS
    0
    0.71
     College
    0.70
    College
    0.69
    université
    0.64
    stab
    0.63
    Edu
    0.63
     Zentrum
    0.63
     Hochschule
    0.63
     Podium
    0.61
    ۰
    0.61
    Activations Density 0.000%

    No Known Activations