© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 192892
    Prev
    Next
    INDEX
    Explanations

    death metal

    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_4_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
    %
    0.94
    ی
    0.82
     composure
    0.80
     pared
    0.79
    یی
    0.79
    ,
    0.78
    A
    0.78
     to
    0.76
    ᆸ
    0.72
    ্য
    0.71
    POSITIVE LOGITS
     attén
    0.87
     ánh
    0.87
    ли
    0.85
     مي
    0.83
     అంద
    0.83
     on
    0.78
     كلمات
    0.77
    re
    0.75
    就是
    0.75
    ？”
    0.75
    Activations Density 0.001%

    No Known Activations