© 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. 90887
    Prev
    Next
    INDEX
    Explanations

    Tokamak, Stonefoot, Stonebeard

    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
    on
    0.96
    ки
    0.93
    ان
    0.91
    0
    0.91
    an
    0.84
    торе
    0.76
    е
    0.75
    or
    0.73
    кина
    0.71
    то
    0.71
    POSITIVE LOGITS
    る
    0.64
     of
    0.63
     וע
    0.57
     Aqui
    0.56
     показатели
    0.56
     daarbij
    0.56
     государ
    0.55
     frá
    0.55
     ngh
    0.54
     Typhoon
    0.54
    Activations Density 0.004%

    No Known Activations