© 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. 62456
    Prev
    Next
    INDEX
    Explanations

    rifles

    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
    Not in Any Lists

    No Comments

    Negative Logits
    т
    0.65
     effectuer
    0.61
     substantiate
    0.59
     Czech
    0.57
     spite
    0.57
     alleging
    0.55
     Utils
    0.54
     certify
    0.54
     CHRIST
    0.54
     prosecuting
    0.54
    POSITIVE LOGITS
    uição
    0.52
    浥
    0.51
    embangunan
    0.48
    ärke
    0.46
     кора
    0.46
    Been
    0.46
    pción
    0.46
    一面
    0.46
     இடை
    0.46
     poderão
    0.45
    Activations Density 0.001%

    No Known Activations