© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 87611
    Prev
    Next
    INDEX
    Explanations

    cups, leagues, diagonal lines

    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_18_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
    物联网
    0.15
     автомоби
    0.14
     автомобиль
    0.14
    filtration
    0.14
     Matlab
    0.14
    hausen
    0.14
     Latinoamérica
    0.14
    =\
    0.14
     melalui
    0.14
    ель
    0.14
    POSITIVE LOGITS
    rā
    0.14
     faintly
    0.13
     elucidate
    0.13
     Usuarios
    0.13
     stderr
    0.13
    rda
    0.13
     rightly
    0.13
    ಧಾರ
    0.13
    ٹو
    0.12
    出一个
    0.12
    Activations Density 0.001%

    No Known Activations