© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39967
    Prev
    Next
    INDEX
    Explanations

    greyman and Business age

    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
    Negative Logits
    il
    1.18
    et
    1.08
    om
    1.05
    au
    1.01
    ag
    0.99
    ot
    0.97
    aras
    0.92
    ens
    0.91
    f
    0.89
    ри
    0.87
    POSITIVE LOGITS
    ని
    0.72
    이랑
    0.72
    ['
    0.71
    >(
    0.68
    দ
    0.68
    ド
    0.68
    /*
    0.67
    이면
    0.67
    
    0.67
    กับ
    0.66
    Activations Density 0.003%

    No Known Activations