© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9217
    Prev
    Next
    INDEX
    Explanations

    foreign or special characters

    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_13_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
    ளுடைய
    0.33
     una
    0.32
     津
    0.32
    uno
    0.32
     Hung
    0.32
    ére
    0.32
    ograd
    0.31
     Ikea
    0.31
     lacked
    0.31
     Sao
    0.31
    POSITIVE LOGITS
     fermeture
    0.35
    ЭС
    0.35
     осіб
    0.34
    గి
    0.33
     bakteri
    0.33
    墓
    0.33
    которы
    0.33
     кою
    0.33
    ܤ
    0.32
    бат
    0.32
    Activations Density 0.022%

    No Known Activations