© 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. 34942
    Prev
    Next
    INDEX
    Explanations

    rubik's cube

    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
    פ
    0.86
    i
    0.85
    ิ
    0.81
    ي
    0.80
    {
    0.80
    。</
    0.79
    י
    0.79
    نا
    0.77
    x
    0.75
    ร
    0.71
    POSITIVE LOGITS
     is
    0.79
    ेंगू
    0.66
    其他
    0.61
    hive
    0.61
    یا
    0.61
    amientos
    0.61
    か
    0.61
    ciò
    0.60
     nơi
    0.59
    देखिए
    0.59
    Activations Density 0.004%

    No Known Activations