© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39371
    Prev
    Next
    INDEX
    Explanations

    开课院系, 开源数据集, GPU

    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
    at
    0.84
     that
    0.74
    р
    0.68
    otta
    0.67
    atot
    0.67
    age
    0.66
     que
    0.66
    that
    0.64
    ﺒ
    0.64
    ോ
    0.63
    POSITIVE LOGITS
     in
    0.66
    mainan
    0.62
     Initialization
    0.62
    lanan
    0.60
     It
    0.60
     [])
    0.59
    kadang
    0.59
    isasi
    0.59
    نی
    0.59
     pengukuran
    0.59
    Activations Density 0.000%

    No Known Activations