© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 157665
    Prev
    Next
    INDEX
    Explanations

    Leonardo

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     lập
    0.45
     Yat
    0.45
    ाइ
    0.38
     Oats
    0.38
     marcher
    0.38
     Angus
    0.37
    齋
    0.37
     Lough
    0.37
     Lash
    0.37
    ュ
    0.37
    POSITIVE LOGITS
     leon
    2.55
     LEON
    2.52
    Leon
    2.42
     Leon
    2.36
    Leonard
    2.33
     Leonard
    2.31
    leon
    2.31
    Leonardo
    2.16
     Leonardo
    2.13
    Leo
    2.08
    Activations Density 0.001%

    No Known Activations