© 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. 122680
    Prev
    Next
    INDEX
    Explanations

    smartphones

    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
    ف
    0.76
    u
    0.76
    ו
    0.70
    ב
    0.70
    점
    0.69
    তা
    0.68
    Smart
    0.66
    サ
    0.66
    מצא
    0.66
    또
    0.65
    POSITIVE LOGITS
    _
    0.86
    {
    0.66
    ни
    0.65
    -
    0.63
    aran
    0.59
     води
    0.59
    он
    0.59
     все
    0.57
     формата
    0.57
     участи
    0.57
    Activations Density 0.002%

    No Known Activations