© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 209963
    Prev
    Next
    INDEX
    Explanations

    specific data

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_43_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
     concord
    0.43
    ghijkl
    0.38
     jav
    0.37
    તિ
    0.37
    गंगा
    0.37
     ব্যাবহার
    0.36
     dersimizde
    0.36
    datetime
    0.36
    샹
    0.36
     როგორ
    0.35
    POSITIVE LOGITS
    そうだ
    0.43
    rank
    0.38
    ี่ยว
    0.38
    muk
    0.37
    ineda
    0.36
    HTT
    0.36
    CES
    0.36
    रिक्त
    0.36
    luca
    0.36
     Guarda
    0.36
    Activations Density 0.000%

    No Known Activations