© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54597
    Prev
    Next
    INDEX
    Explanations

    different password

    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_31_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
     Ezekiel
    0.31
     лиде
    0.29
     ملاقات
    0.29
    ช่อง
    0.28
     형
    0.28
     jurid
    0.28
    }|=
    0.27
    澗
    0.27
     მან
    0.27
     лидер
    0.27
    POSITIVE LOGITS
     volcano
    0.28
    клары
    0.28
     diaria
    0.28
     चांदनी
    0.27
    ოთ
    0.27
     MinMaxScaler
    0.27
     আট
    0.27
     Meridian
    0.26
    ोब
    0.26
    atkar
    0.26
    Activations Density 0.000%

    No Known Activations