© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 203111
    Prev
    Next
    INDEX
    Explanations

    fixed-length numerical vector

    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_37_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
     AppException
    0.42
    linien
    0.40
    讲话
    0.38
     ٿ
    0.38
     agam
    0.38
    wang
    0.37
    tre
    0.35
    一层
    0.35
    Tre
    0.35
    enton
    0.35
    POSITIVE LOGITS
     arrays
    0.96
     array
    0.91
    Arrays
    0.88
    数组
    0.87
     Arrays
    0.86
    array
    0.83
    arrays
    0.81
    陣
    0.77
     Array
    0.73
    阵
    0.72
    Activations Density 0.008%

    No Known Activations