© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124829
    Prev
    Next
    INDEX
    Explanations

    Fairy tale, hiring, competition, testing

    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
    在
    0.73
    a
    0.70
    지만
    0.66
     are
    0.65
    取り
    0.64
    的
    0.63
    ंग
    0.62
     ایسا
    0.62
    كا
    0.62
     pecados
    0.62
    POSITIVE LOGITS
    ur
    0.82
    AL
    0.77
    AG
    0.72
    to
    0.68
    ORE
    0.68
    APT
    0.66
    UR
    0.62
    urar
    0.62
    ิ
    0.61
    ut
    0.60
    Activations Density 0.005%

    No Known Activations