© 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. 33858
    Prev
    Next
    INDEX
    Explanations

    veloci

    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
    <0x80>
    0.97
    もら
    0.75
    ᅦ
    0.74
    ри
    0.73
    ра
    0.73
    {
    0.72
    ח
    0.71
    не
    0.71
    ين
    0.70
    もり
    0.70
    POSITIVE LOGITS
     that
    0.75
     of
    0.70
    ’
    0.68
    al
    0.68
    <h3>
    0.66
     pickles
    0.59
     Phases
    0.59
     Hike
    0.59
    <h4>
    0.59
    ΟΥ
    0.58
    Activations Density 0.006%

    No Known Activations