© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 47706
    Prev
    Next
    INDEX
    Explanations

    require statements

    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_10_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
    ாக
    1.06
    ت
    0.87
     an
    0.75
     ovipares
    0.66
    !",
    0.65
     !",
    0.64
     It
    0.64
     critters
    0.63
     hér
    0.62
     longa
    0.61
    POSITIVE LOGITS
    да
    0.97
    را
    0.80
     in
    0.78
    w
    0.78
     в
    0.77
    ного
    0.73
     තුළ
    0.73
    문
    0.72
    in
    0.72
    wa
    0.70
    Activations Density 0.005%

    No Known Activations