© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91596
    Prev
    Next
    INDEX
    Explanations

    arm circles and commissions

    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_3_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
    um
    0.89
    é
    0.77
    ang
    0.76
    ak
    0.73
    t
    0.70
    p
    0.69
    ag
    0.66
    im
    0.63
    un
    0.61
    y
    0.61
    POSITIVE LOGITS
    K
    0.63
    サ
    0.63
     to
    0.61
    ).
    0.60
     atteint
    0.60
     goble
    0.60
     lard
    0.60
    行動
    0.60
    の影響
    0.60
     Accesat
    0.59
    Activations Density 0.002%

    No Known Activations