© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 42453
    Prev
    Next
    INDEX
    Explanations

    pets and operating systems

    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_13_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
     eres
    0.48
     ن
    0.47
     Chilean
    0.47
    一片
    0.47
    alne
    0.46
    💪
    0.46
    atica
    0.45
    に入る
    0.45
    Altitude
    0.45
     !}
    0.45
    POSITIVE LOGITS
    ándola
    0.45
    lew
    0.44
    POINTS
    0.44
     เนาะ
    0.43
    िमा
    0.43
    ियों
    0.42
    IPS
    0.41
    points
    0.41
    vén
    0.41
    OLD
    0.41
    Activations Density 0.035%

    No Known Activations