© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42503
    Prev
    Next
    INDEX
    Explanations

    City Palace

    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
    c
    0.92
    ى
    0.75
     in
    0.70
    t
    0.69
     في
    0.68
    et
    0.64
     insect
    0.64
    k
    0.63
    ம்
    0.62
    开
    0.62
    POSITIVE LOGITS
     بگیر
    0.68
    ਡ
    0.68
    𝗙
    0.66
    فی
    0.63
    ΜΑ
    0.60
     chaude
    0.60
    HOME
    0.59
    거
    0.59
    ویت
    0.59
     न्याया
    0.58
    Activations Density 0.001%

    No Known Activations