© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35961
    Prev
    Next
    INDEX
    Explanations

    masulipatnam, muhammed, muhammadur rasulullah

    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
    在
    1.08
    و
    0.74
    ل
    0.72
    س
    0.68
    to
    0.67
    可以
    0.66
    os
    0.66
    منا
    0.65
    mand
    0.64
    ver
    0.64
    POSITIVE LOGITS
     on
    0.69
     venit
    0.68
     are
    0.67
    शिप
    0.67
     assaulting
    0.66
    یی
    0.64
    :
    0.64
    یم
    0.61
     dan
    0.60
    selling
    0.60
    Activations Density 0.000%

    No Known Activations