© 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. 39759
    Prev
    Next
    INDEX
    Explanations

    way forward

    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
    的区别
    0.71
     uitgenodigd
    0.70
     camped
    0.68
     are
    0.66
    の
    0.64
     trusty
    0.63
     perdu
    0.62
     collectif
    0.62
     đợi
    0.61
    ale
    0.60
    POSITIVE LOGITS
    that
    0.92
    ת
    0.91
    ล
    0.83
    ל
    0.80
    ర్
    0.71
    ק
    0.71
    ता
    0.70
    ם
    0.69
    wirtschaft
    0.66
    ก
    0.66
    Activations Density 0.000%

    No Known Activations