© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193780
    Prev
    Next
    INDEX
    Explanations

    periods; hours; long

    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_27_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
    massive
    0.37
    Ƌ
    0.37
    disciplinary
    0.37
    luent
    0.36
     treason
    0.36
     ሙሉ
    0.36
     দেরী
    0.36
    விர
    0.36
     молодой
    0.36
    thias
    0.36
    POSITIVE LOGITS
    underset
    0.36
     mined
    0.36
    磪
    0.35
    _{\
    0.34
     connectedness
    0.34
     জী
    0.33
     отре
    0.33
    Screen
    0.33
     مت
    0.33
     Screen
    0.33
    Activations Density 0.000%

    No Known Activations