© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229668
    Prev
    Next
    INDEX
    Explanations

    high aspect ratio, bandwidth, measurement

    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_6_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
    ᱐
    0.88
    az
    0.86
    0
    0.83
    
    0.83
     alebo
    0.83
    Ṕ
    0.82
    ０
    0.82
     домаћин
    0.81
     Maugin
    0.80
    oq
    0.77
    POSITIVE LOGITS
     an
    1.54
    ت
    0.96
     It
    0.93
    k
    0.92
    ת
    0.91
    ก
    0.89
    в
    0.82
    ל
    0.82
     wheel
    0.81
    h
    0.81
    Activations Density 0.015%

    No Known Activations