© 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. 41340
    Prev
    Next
    INDEX
    Explanations

    Lockheed Martin and councils

    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
    ে
    0.84
    ↵
    0.76
    ي
    0.73
    י
    0.72
    i
    0.71
    ert
    0.70
    ü
    0.65
    ，「
    0.62
    ↵↵
    0.62
    ຳ
    0.59
    POSITIVE LOGITS
    ための
    0.79
    闶
    0.77
    నూ
    0.69
    oja
    0.67
    s
    0.63
    大力
    0.62
    🪐
    0.62
    ز
    0.61
     Melo
    0.60
    酉
    0.59
    Activations Density 0.002%

    No Known Activations