© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24106
    Prev
    Next
    INDEX
    Explanations

    mammals

    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
    Negative Logits
    یم
    0.86
    اتی
    0.79
    シーン
    0.77
     scène
    0.76
    능
    0.75
     !")
    0.68
    면
    0.68
    ि
    0.67
    지
    0.66
    ق
    0.65
    POSITIVE LOGITS
    rat
    0.70
    s
    0.70
    sion
    0.66
     enz
    0.63
    /*
    0.62
     pavatt
    0.62
    ra
    0.62
    fifth
    0.61
    ong
    0.61
    man
    0.61
    Activations Density 0.003%

    No Known Activations