© 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. 36284
    Prev
    Next
    INDEX
    Explanations

    k-Nearest Neighbors

    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
    om
    0.93
    ay
    0.92
    ong
    0.85
    리
    0.85
    リ
    0.84
    au
    0.80
    ss
    0.79
    ym
    0.76
    ser
    0.76
    SC
    0.76
    POSITIVE LOGITS
    ی
    0.84
     Rajya
    0.68
    ią
    0.66
    '>
    0.65
    ۹
    0.63
     enunci
    0.63
    િ
    0.59
     pertin
    0.58
    ()'
    0.57
     suppuration
    0.56
    Activations Density 0.052%

    No Known Activations