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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5501
    Prev
    Next
    INDEX
    Explanations

    asegúrate de

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
    ी
    2.54
    ে
    2.38
    ์
    2.05
    ು
    1.76
    ce
    1.69
     mitt
    1.69
    ו
    1.69
    ف
    1.62
    й
    1.61
    mdash
    1.61
    POSITIVE LOGITS
     MyHomePage
    2.00
    ات
    1.98
     Earrings
    1.80
     NuGet
    1.71
     asymptotic
    1.71
     Strongly
    1.70
    heuristic
    1.69
     солнца
    1.68
     ordinate
    1.68
     solemnly
    1.68
    Activations Density 0.001%

    No Known Activations