© 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. 206442
    Prev
    Next
    INDEX
    Explanations

    time period

    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
    is
    0.89
    ه
    0.76
    ک
    0.73
    کم
    0.71
    تر
    0.71
    یس
    0.71
    گ
    0.69
    ده
    0.69
    ↵↵
    0.65
    ने
    0.64
    POSITIVE LOGITS
     univerz
    0.79
     rask
    0.77
     VGM
    0.76
     werk
    0.74
    <unused325>
    0.73
     an
    0.73
     szyb
    0.72
     jeden
    0.72
     stare
    0.71
     sombre
    0.71
    Activations Density 0.003%

    No Known Activations