© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199317
    Prev
    Next
    INDEX
    Explanations

    unpacking complexity

    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_12_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
     對
    0.38
     รวม
    0.38
    nione
    0.38
     und
    0.38
    सँग
    0.38
    li
    0.37
     uner
    0.37
    OLOGY
    0.37
     demonstra
    0.37
     多
    0.36
    POSITIVE LOGITS
    ävä
    0.40
    ierrez
    0.39
    グリ
    0.38
    ים
    0.37
     کیسینو
    0.37
    ร
    0.36
    یس
    0.36
    ävät
    0.36
    イク
    0.35
    ポジ
    0.35
    Activations Density 0.001%

    No Known Activations