© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58802
    Prev
    Next
    INDEX
    Explanations

    sports analysis and performance data

    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_11_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
    し
    0.49
     volts
    0.47
    はい
    0.46
     contro
    0.46
     isra
    0.46
     harsh
    0.46
     ampl
    0.45
     perl
    0.45
    わた
    0.45
     sculptural
    0.44
    POSITIVE LOGITS
    ۔
    0.52
     Л
    0.46
    riving
    0.45
    闶
    0.44
     М
    0.43
    olong
    0.43
    ̀ng
    0.43
     т
    0.43
    ilin
    0.43
    iterranean
    0.41
    Activations Density 0.026%

    No Known Activations