© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76731
    Prev
    Next
    INDEX
    Explanations

    related to delimited data or lists

    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_31_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
    朳
    0.06
     thấm
    0.06
    وين
    0.06
    แน่น
    0.06
     காலை
    0.06
    <unused2188>
    0.06
    ेंस
    0.06
     аппарат
    0.06
    权重
    0.06
     Reaktion
    0.06
    POSITIVE LOGITS
     aqu
    0.07
    Del
    0.07
    鴉
    0.07
    del
    0.06
    punk
    0.06
    jó
    0.06
    bev
    0.06
    Bev
    0.06
     Del
    0.06
    vre
    0.06
    Activations Density 0.008%

    No Known Activations