© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25251
    Prev
    Next
    INDEX
    Explanations

    through the lens

    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_10_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
    ED
    0.17
     područ
    0.17
    siniz
    0.17
    IT
    0.17
    IC
    0.16
    ction
    0.16
    ंना
    0.16
    み
    0.16
    った
    0.16
     。
    0.16
    POSITIVE LOGITS
    ها
    0.17
     Христос
    0.17
    ਾ
    0.16
    િ
    0.16
    ంక
    0.15
     Йо
    0.15
    aut
    0.15
     Gand
    0.15
     सो
    0.15
     aberr
    0.15
    Activations Density 0.006%

    No Known Activations