© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46283
    Prev
    Next
    INDEX
    Explanations

    academic achievement in schools

    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_13_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
     karde
    0.52
    adı
    0.51
    🇲
    0.51
     çünkü
    0.50
    因为
    0.47
     İslam
    0.46
    🇹
    0.46
    ricted
    0.46
     alanı
    0.46
     perché
    0.45
    POSITIVE LOGITS
    uy
    0.51
    ER
    0.47
     пись
    0.47
    蠣
    0.47
    te
    0.47
    cych
    0.46
    ^{
    0.46
    ীরে
    0.46
    ge
    0.46
    спери
    0.46
    Activations Density 0.041%

    No Known Activations