© 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. 42871
    Prev
    Next
    INDEX
    Explanations

    Francis Collins, Bacon, Crick, Church

    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
     تحميل
    0.65
     غير
    0.63
     ($_
    0.63
     يوم
    0.61
     have
    0.60
    いを
    0.59
    ج
    0.59
    جين
    0.58
    ને
    0.58
     zacz
    0.57
    POSITIVE LOGITS
    in
    0.80
    لی
    0.80
    ン
    0.69
    ב
    0.67
     is
    0.67
    )"
    0.65
    мець
    0.65
    was
    0.64
    ė
    0.63
    𝚖
    0.63
    Activations Density 0.000%

    No Known Activations