© 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. 194641
    Prev
    Next
    INDEX
    Explanations

    screen tearing, contracts, auction, bidding

    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
     femelles
    0.55
     buildFor
    0.51
     capacitances
    0.51
     কমি
    0.50
    倠
    0.50
     caché
    0.49
     económica
    0.48
     capacidades
    0.47
     económicas
    0.47
    َر
    0.47
    POSITIVE LOGITS
    kti
    0.58
    Интернет
    0.56
     যাদ
    0.55
    ГИ
    0.53
    सार
    0.52
    Ч
    0.52
    Ⅰ
    0.52
    中山
    0.51
    Фу
    0.51
    П
    0.50
    Activations Density 0.000%

    No Known Activations