© 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. 50552
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    y
    0.53
    -
    0.51
     system
    0.51
    viation
    0.49
     research
    0.48
    ations
    0.48
    i
    0.48
    ation
    0.46
    handed
    0.46
     is
    0.46
    POSITIVE LOGITS
     ਅਤੇ
    0.56
    ン
    0.54
     ಹೊಂದ
    0.53
    ੁੰ
    0.53
    用餐
    0.53
     ಸಾಧ್ಯ
    0.52
    ㄼ
    0.52
    겟
    0.51
     дороге
    0.50
     ತುಂಬಾ
    0.50
    Activations Density 0.000%

    No Known Activations