© 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. 216844
    Prev
    Next
    INDEX
    Explanations

    One Hundred Years of Solitude

    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
     ابو
    0.39
    鸿
    0.39
    สะ
    0.38
    ্ধ্য
    0.38
     soothing
    0.37
     lubricating
    0.36
     PVC
    0.36
     Лю
    0.36
    สิ่งที่
    0.36
    akk
    0.35
    POSITIVE LOGITS
    getR
    0.46
    R
    0.45
    unii
    0.43
     Р
    0.42
    ási
    0.42
     Bells
    0.42
     R
    0.41
     நடந்த
    0.41
     Rabbit
    0.41
    Rabbit
    0.41
    Activations Density 0.000%

    No Known Activations