© 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. 122686
    Prev
    Next
    INDEX
    Explanations

    business district and facilities

    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
    ů
    0.63
     comple
    0.58
    raspberry
    0.58
    t
    0.58
     nhàng
    0.57
    рован
    0.56
    磊
    0.55
    ारखंड
    0.54
     الزد
    0.54
     is
    0.52
    POSITIVE LOGITS
    س
    0.71
    ن
    0.70
    기
    0.70
    ش
    0.68
    ك
    0.65
    (
    0.64
    \
    0.62
     for
    0.61
    」、
    0.59
    "，
    0.59
    Activations Density 0.001%

    No Known Activations