© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 213588
    Prev
    Next
    INDEX
    Explanations

    word starts

    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_50_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
    пи
    0.89
    ピ
    0.87
     пи
    0.85
    pi
    0.82
    พิ
    0.82
    Пи
    0.82
     Пи
    0.81
    pid
    0.80
     피
    0.79
    피
    0.79
    POSITIVE LOGITS
     epoch
    0.42
    apha
    0.42
     EPO
    0.41
    epa
    0.40
     rapt
    0.40
     découvrir
    0.40
     springer
    0.40
    Pho
    0.39
    EPO
    0.39
     ез
    0.39
    Activations Density 0.003%

    No Known Activations