© 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. 34412
    Prev
    Next
    INDEX
    Explanations

    fifty percent

    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
    ü
    0.76
    ung
    0.71
    eluarkan
    0.68
    ors
    0.66
    ande
    0.65
    ли
    0.63
    ை
    0.63
    Y
    0.61
    ב
    0.61
    ouden
    0.61
    POSITIVE LOGITS
     zwią
    0.75
    م
    0.72
    方法
    0.71
    m
    0.69
     voglio
    0.69
     méth
    0.68
     trạng
    0.66
     dưới
    0.65
     đọc
    0.65
     структура
    0.64
    Activations Density 0.002%

    No Known Activations