© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 41211
    Prev
    Next
    INDEX
    Explanations

    Jonah Hill, Rahm, Jump, Bank, Ray, Kim Jong-un

    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_3_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
     переда
    0.71
     fracción
    0.69
    ่
    0.60
     tật
    0.60
     imparting
    0.59
     undergoing
    0.58
    박
    0.58
     pequeñas
    0.57
     препарата
    0.56
     передачи
    0.56
    POSITIVE LOGITS
    is
    0.62
    .
    0.60
     kur
    0.55
    _
    0.55
    as
    0.55
     kter
    0.54
    Rs
    0.52
    weite
    0.52
    ها
    0.52
    Chart
    0.51
    Activations Density 0.001%

    No Known Activations