© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 135137
    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_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
    的な
    0.83
    ینه
    0.80
    ני
    0.76
    ТИ
    0.76
    이란
    0.75
    i
    0.75
     غیر
    0.75
    ン
    0.74
    แรม
    0.73
    ہنی
    0.73
    POSITIVE LOGITS
     It
    0.91
    ä
    0.88
    ay
    0.77
    ف
    0.71
    ,?
    0.69
    ,",
    0.68
    ð
    0.67
    is
    0.65
    0.65
    to
    0.64
    Activations Density 0.000%

    No Known Activations