© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 100712
    Prev
    Next
    INDEX
    Explanations

    director, conductor, Maestro

    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_16_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
    ೇಳ
    0.59
    넥
    0.50
     acheté
    0.46
    얇
    0.46
    gnet
    0.45
    舒適
    0.45
    鈴木
    0.44
    ွား
    0.44
    ያዎች
    0.44
     কর্তৃপক্ষের
    0.44
    POSITIVE LOGITS
    Duration
    0.54
    acidad
    0.52
    wo
    0.49
    Kota
    0.48
    afa
    0.46
    ill
    0.46
     I
    0.45
    ascimento
    0.45
     powinien
    0.45
    ff
    0.44
    Activations Density 0.001%

    No Known Activations