© 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. 89123
    Prev
    Next
    INDEX
    Explanations

    date for dates and documents

    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
     THEIR
    0.67
    MENTS
    0.62
    y
    0.62
    OWN
    0.61
    ILAR
    0.61
     tiempo
    0.59
     כל
    0.59
     actuales
    0.58
     ﺍ
    0.58
     mismas
    0.57
    POSITIVE LOGITS
    to
    0.68
    by
    0.61
    feeding
    0.61
     notebook
    0.58
     Jameson
    0.58
    of
    0.57
    get
    0.56
    ov
    0.56
     to
    0.55
    getStudentNo
    0.55
    Activations Density 0.001%

    No Known Activations