© 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. 207031
    Prev
    Next
    INDEX
    Explanations

    ScienceDirect, Safeway

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    for
    0.74
    :
    0.66
    ldon
    0.61
    bulb
    0.59
    ourses
    0.59
    ht
    0.57
     extrapol
    0.57
     for
    0.55
    monds
    0.55
    ppet
    0.53
    POSITIVE LOGITS
    もら
    0.95
    も
    0.85
    在
    0.83
     in
    0.80
    ও
    0.77
    سي
    0.71
    도
    0.71
     في
    0.69
     còn
    0.68
    ة
    0.68
    Activations Density 0.000%

    No Known Activations