© 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. 38621
    Prev
    Next
    INDEX
    Explanations

    MrBeast, President

    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
    o
    0.75
    I
    0.68
    al
    0.63
    u
    0.57
    M
    0.56
    ä
    0.56
    September
    0.55
    DUCT
    0.55
    ia
    0.54
    A
    0.54
    POSITIVE LOGITS
    দের
    0.87
    いる
    0.71
     ສ
    0.70
     Оде
    0.69
     degli
    0.68
    ের
    0.66
     ライト
    0.65
     dangereux
    0.64
    রি
    0.63
    ع
    0.63
    Activations Density 0.000%

    No Known Activations