© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 236509
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_32_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
    Expense
    0.36
    枯
    0.35
    judul
    0.32
     jornada
    0.32
    образие
    0.32
    ёма
    0.32
    Tama
    0.32
    neos
    0.31
    Doch
    0.31
    班
    0.31
    POSITIVE LOGITS
    getInstalled
    0.35
     Meteorological
    0.34
     meteorological
    0.34
    拷
    0.34
     गणित
    0.34
     छैन
    0.33
     verhindern
    0.33
     Pompe
    0.33
     Hadoop
    0.32
     happens
    0.32
    Activations Density 0.000%

    No Known Activations