© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56984
    Prev
    Next
    INDEX
    Explanations

    of self

    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_11_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
    /
    0.77
    =
    0.71
    u
    0.70
    er
    0.67
    ifts
    0.63
    iling
    0.62
    ا
    0.61
    。
    0.60
    '
    0.59
    per
    0.58
    POSITIVE LOGITS
     cristiana
    0.82
     створи
    0.72
     fuori
    0.71
     itd
    0.69
     書い
    0.69
     ABOUT
    0.68
     mischiev
    0.68
     אבי
    0.68
     jemand
    0.67
     levou
    0.67
    Activations Density 0.001%

    No Known Activations