© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 199609
    Prev
    Next
    INDEX
    Explanations

    relation into type

    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_15_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
    烨
    0.54
    ène
    0.52
     justiça
    0.52
     Diseases
    0.51
     انڈیا
    0.51
    ణా
    0.49
     नवीनतम
    0.48
    阌
    0.48
     ine
    0.47
     Sanskrit
    0.47
    POSITIVE LOGITS
    %
    0.55
    argento
    0.50
    offset
    0.50
    class
    0.49
    レオ
    0.48
     are
    0.47
    avljen
    0.47
    esteem
    0.47
     anciennes
    0.46
    emas
    0.46
    Activations Density 0.000%

    No Known Activations