© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200243
    Prev
    Next
    INDEX
    Explanations

    looping constructs, templating engines

    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_12_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
    $，
    0.65
    ッピング
    0.59
    RAIT
    0.54
    謃
    0.53
    mobilpay
    0.52
    ⟣
    0.52
     préférences
    0.52
     receptacles
    0.52
    ούς
    0.52
     মোটা
    0.51
    POSITIVE LOGITS
     Season
    0.61
     February
    0.58
     tahun
    0.54
     year
    0.54
     Chinese
    0.52
     season
    0.52
     Engines
    0.51
    0.51
    *
    0.51
     dawn
    0.51
    Activations Density 0.001%

    No Known Activations