© 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. 42118
    Prev
    Next
    INDEX
    Explanations

    gargle with

    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
     来
    0.90
    d
    0.87
    后
    0.83
    来
    0.73
    一個
    0.71
    这
    0.71
    儡
    0.71
     來
    0.70
     在
    0.68
    并
    0.68
    POSITIVE LOGITS
    im
    0.89
    to
    0.85
    ak
    0.71
    ین
    0.71
    αν
    0.70
    I
    0.70
    as
    0.70
    an
    0.69
    the
    0.69
    0
    0.68
    Activations Density 0.000%

    No Known Activations