© 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. 78342
    Prev
    Next
    INDEX
    Explanations

    html canvas display

    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
    िलों
    0.40
    iscid
    0.38
     antérieurs
    0.38
    Innen
    0.38
    ತನ
    0.38
    糕
    0.37
    iston
    0.36
    Chocolate
    0.36
    harga
    0.36
    η
    0.35
    POSITIVE LOGITS
     multiplicação
    0.40
     ಅಭ
    0.39
    బో
    0.37
     Monitors
    0.37
     aproxim
    0.35
     monit
    0.34
     صع
    0.33
    ंडा
    0.33
     ندا
    0.33
     المتوسط
    0.33
    Activations Density 0.002%

    No Known Activations