© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13814
    Prev
    Next
    INDEX
    Explanations

    speed

    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_40_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
    嗲
    0.37
     zicht
    0.36
    setAction
    0.35
    ຊ
    0.35
    chens
    0.34
    定了
    0.34
     Maraton
    0.33
    珵
    0.33
    DropdownBox
    0.33
    栢
    0.33
    POSITIVE LOGITS
     скорости
    0.55
     vitesse
    0.52
    速度
    0.51
     speeds
    0.50
     velocidades
    0.47
     velocidad
    0.46
     سرعت
    0.46
     vitesses
    0.45
     скорость
    0.44
     velocities
    0.44
    Activations Density 0.238%

    No Known Activations