© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88581
    Prev
    Next
    INDEX
    Explanations

    ความสัมพันธ์, เวลา, ส่วน

    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
    <0xF3>
    0.76
    تعليم
    0.75
    1
    0.74
    、“
    0.70
    ”;
    0.69
     е
    0.66
    ن
    0.66
    出
    0.66
    část
    0.64
    }=\
    0.64
    POSITIVE LOGITS
    u
    1.13
     sacrament
    0.74
    an
    0.73
    t
    0.70
    .
    0.70
    ні
    0.65
     berita
    0.65
    ing
    0.65
    usakan
    0.65
    d
    0.63
    Activations Density 0.001%

    No Known Activations