© 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. 121979
    Prev
    Next
    INDEX
    Explanations

    Earthlings or orbit

    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
    АТ
    0.60
     servidores
    0.59
    و
    0.59
     be
    0.58
     vestiges
    0.57
    乨
    0.57
    ক্ষেত্র
    0.56
    ЕМ
    0.55
     reverts
    0.55
    |$,
    0.54
    POSITIVE LOGITS
    end
    0.82
    ey
    0.73
    ä
    0.69
    mist
    0.68
    5
    0.68
    ang
    0.67
    lik
    0.66
    2
    0.66
    ra
    0.64
    green
    0.64
    Activations Density 0.001%

    No Known Activations