© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 57740
    Prev
    Next
    INDEX
    Explanations

    các nguyên tắc và khái niệm

    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_2_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ки
    1.28
     on
    1.16
    ق
    1.01
    त
    0.97
    на
    0.96
    其他
    0.95
    д
    0.89
    ત
    0.89
    on
    0.88
    ب
    0.88
    POSITIVE LOGITS
    '
    0.84
    ’
    0.71
    ،
    0.68
    rdquo
    0.58
    iatric
    0.55
    orems
    0.55
    ".
    0.54
     a
    0.52
    ，
    0.52
     argumentation
    0.52
    Activations Density 0.002%

    No Known Activations