© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 192835
    Prev
    Next
    INDEX
    Explanations

    would be

    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_4_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
     mouve
    0.93
     atteint
    0.91
     cortar
    0.91
     ομά
    0.90
    س
    0.89
    ن
    0.87
     apparaît
    0.86
     éto
    0.86
    نہ
    0.85
     ejecutar
    0.85
    POSITIVE LOGITS
    지
    1.25
    of
    1.02
    so
    1.00
    ze
    0.93
    te
    0.90
    ка
    0.90
    та
    0.88
    the
    0.86
     e
    0.85
    u
    0.85
    Activations Density 0.003%

    No Known Activations