© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126663
    Prev
    Next
    INDEX
    Explanations

    Kill la Kill

    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
    re
    0.68
    ِي
    0.65
    י
    0.62
    de
    0.62
     Temperatur
    0.61
    li
    0.61
    ne
    0.58
    ي
    0.58
     "")
    0.57
     rhiz
    0.57
    POSITIVE LOGITS
    ای
    0.72
    ის
    0.70
    기
    0.69
     sytuacji
    0.66
    אר
    0.66
    σε
    0.65
     הפ
    0.64
     atteint
    0.64
    ことにより
    0.64
     mesma
    0.63
    Activations Density 0.014%

    No Known Activations