© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 139120
    Prev
    Next
    INDEX
    Explanations

    Hue

    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_37_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
    ंख्य
    0.39
    acterium
    0.38
     कार्यकार
    0.37
     Crazy
    0.37
     економі
    0.37
    кономи
    0.37
    лько
    0.36
    ="../../../../
    0.36
    drig
    0.35
     коричне
    0.35
    POSITIVE LOGITS
     hours
    0.96
    Hours
    0.93
     Hours
    0.92
     hour
    0.86
     Hour
    0.83
    hours
    0.81
     Stunden
    0.81
     HOURS
    0.80
     horas
    0.79
     HOUR
    0.79
    Activations Density 0.002%

    No Known Activations