© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46795
    Prev
    Next
    INDEX
    Explanations

    i love

    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_13_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
    初
    0.56
     prayers
    0.44
     Prevention
    0.44
    s
    0.44
    工程
    0.44
    ऱ्यांना
    0.44
    病情
    0.43
     پیدا
    0.43
    전
    0.42
    受注
    0.42
    POSITIVE LOGITS
     там
    0.44
     herring
    0.43
     к
    0.42
     ஃ
    0.41
     ".
    0.40
     bowiem
    0.40
     transversal
    0.39
    нки
    0.39
     ф
    0.39
    uctive
    0.39
    Activations Density 0.002%

    No Known Activations