© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 158811
    Prev
    Next
    INDEX
    Explanations

    music artists and releases

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    odet
    0.44
    エントリー
    0.42
    osing
    0.41
     Hunter
    0.41
    杭
    0.41
    oes
    0.40
    埃及
    0.40
    Lucky
    0.40
     Geek
    0.39
    ೋದ
    0.38
    POSITIVE LOGITS
     Am
    0.44
    Am
    0.44
     Preprint
    0.40
     Mey
    0.39
     ross
    0.38
    惯
    0.38
    鎊
    0.38
     Oliver
    0.37
     Nevertheless
    0.36
     grunds
    0.36
    Activations Density 0.000%

    No Known Activations