© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 46616
    Prev
    Next
    INDEX
    Explanations

    PCM, PSK, PVC, CPC

    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_10_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
    วัน
    0.70
    are
    0.66
    𝙎
    0.64
     antioxidants
    0.63
    𝑺
    0.63
    णी
    0.62
    एस
    0.60
    डा
    0.60
    atching
    0.60
    眄
    0.60
    POSITIVE LOGITS
    يد
    0.90
    ב
    0.77
     damals
    0.71
    <0x0D>
    0.70
    פ
    0.69
    al
    0.69
     früher
    0.68
     frühen
    0.68
    _
    0.66
    OL
    0.65
    Activations Density 0.003%

    No Known Activations