© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 65836
    Prev
    Next
    INDEX
    Explanations

    Tam

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_51_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
     luyện
    0.64
    煉
    0.61
     лю
    0.56
     Lumber
    0.56
     Lutheran
    0.54
     Лу
    0.53
     лу
    0.53
     Lug
    0.52
    卢
    0.52
    練習
    0.52
    POSITIVE LOGITS
     tầm
    0.88
     Tamm
    0.78
     Tammy
    0.73
    tam
    0.72
     TAM
    0.72
     tam
    0.69
    Tam
    0.68
    TAM
    0.68
    Tama
    0.64
    atam
    0.64
    Activations Density 0.000%

    No Known Activations