© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 34969
    Prev
    Next
    INDEX
    Explanations

    shuffle forward, in, down, over

    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_11_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
    foils
    0.72
     ಹೇ
    0.71
    bleeds
    0.69
    𝙙
    0.68
     않는
    0.66
     सहज
    0.65
     ର
    0.64
    𝙛
    0.64
     사용하는
    0.63
    utors
    0.62
    POSITIVE LOGITS
    ين
    0.80
    Ка
    0.77
    O
    0.74
    По
    0.71
    Ви
    0.69
    一
    0.69
     inici
    0.68
    Кон
    0.68
    【
    0.67
    Ве
    0.67
    Activations Density 0.001%

    No Known Activations