© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 79115
    Prev
    Next
    INDEX
    Explanations

    quadratic

    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_53_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
     пора
    0.41
     أت
    0.41
    issus
    0.40
    弼
    0.39
    抜き
    0.39
    सित
    0.38
     Perm
    0.37
    ateau
    0.37
    የት
    0.37
    eper
    0.37
    POSITIVE LOGITS
    Quadr
    0.43
     Quadr
    0.40
     candlestick
    0.39
     вари
    0.39
    酰
    0.39
    ํ
    0.38
     quadratic
    0.36
    wür
    0.36
    counterx
    0.36
    mann
    0.36
    Activations Density 0.001%

    No Known Activations