© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 93489
    Prev
    Next
    INDEX
    Explanations

    code and models

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    9
    1.96
    <0xBF>
    1.88
     nine
    1.77
    ９
    1.72
     девя
    1.70
    九
    1.67
     ۹
    1.66
     Nine
    1.66
     ৯
    1.60
     ninety
    1.58
    POSITIVE LOGITS
    <unused74>
    0.42
    <unused84>
    0.39
    SalesRep
    0.39
    ையைக்
    0.36
     دینا
    0.35
     funcionalidad
    0.35
     eighteenth
    0.34
     வடிவ
    0.34
    xima
    0.34
     இன
    0.34
    Activations Density 0.088%

    No Known Activations