© 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. 127241
    Prev
    Next
    INDEX
    Explanations

    flip flop, bus, flow, magic, surrogate

    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
    من
    0.75
     Dham
    0.73
    ی
    0.72
    s
    0.69
    It
    0.67
    If
    0.67
    عمل
    0.67
    Flat
    0.66
    AI
    0.65
    ৪
    0.65
    POSITIVE LOGITS
    '
    0.86
    ла
    0.71
    uencia
    0.68
     sûr
    0.68
     vieron
    0.66
    oing
    0.65
     resuscitation
    0.64
     particulate
    0.62
    ról
    0.62
    ielles
    0.62
    Activations Density 0.009%

    No Known Activations