© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29509
    Prev
    Next
    INDEX
    Explanations

    对...的建议/影响/区别

    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_10_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
     нагрузки
    0.73
    inoa
    0.72
    issait
    0.69
    omass
    0.69
    𝟬
    0.69
     двох
    0.68
     जड़ों
    0.68
     정의역
    0.66
     outcrops
    0.66
    <0x94>
    0.65
    POSITIVE LOGITS
    на
    0.82
    i
    0.74
    e
    0.74
    ва
    0.72
     ADA
    0.69
    の
    0.68
    g
    0.68
    Name
    0.66
     KGB
    0.66
    es
    0.65
    Activations Density 0.001%

    No Known Activations