© 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. 35006
    Prev
    Next
    INDEX
    Explanations

    Sea or Road

    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
    ной
    0.79
    1
    0.77
    druck
    0.68
    dien
    0.68
    ﺕ
    0.67
    dé
    0.63
    ದೇಶ
    0.62
    ᱼ
    0.61
    ных
    0.61
    ющих
    0.61
    POSITIVE LOGITS
    н
    0.77
    น
    0.75
    ла
    0.71
    ক
    0.63
    是
    0.55
    {//
    0.54
    ن
    0.53
    сков
    0.53
    ン
    0.53
    从小
    0.52
    Activations Density 0.001%

    No Known Activations