© 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. 39450
    Prev
    Next
    INDEX
    Explanations

    hands-free control

    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
    ⇰
    0.66
    柇
    0.62
    in
    0.59
    ᱽ
    0.58
    제를
    0.57
    ið
    0.57
    直線
    0.56
    まずは
    0.56
    ૨
    0.56
    lower
    0.55
    POSITIVE LOGITS
     to
    0.86
     was
    0.84
     are
    0.76
     is
    0.75
     has
    0.73
    する
    0.70
    ene
    0.65
    なった
    0.65
    <0xA6>
    0.65
    ся
    0.65
    Activations Density 0.003%

    No Known Activations