© 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. 90330
    Prev
    Next
    INDEX
    Explanations

    Russian Federation

    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
    ન
    0.77
     recib
    0.71
     renfer
    0.69
     atteindre
    0.69
     conclu
    0.67
     potenci
    0.66
     importantes
    0.64
     anunci
    0.64
    н
    0.64
     cinqui
    0.64
    POSITIVE LOGITS
    s
    0.93
    ों
    0.87
    os
    0.77
    ang
    0.76
    ો
    0.72
    é
    0.70
    bs
    0.70
    Are
    0.70
    ip
    0.69
    0
    0.69
    Activations Density 0.001%

    No Known Activations