© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 130668
    Prev
    Next
    INDEX
    Explanations

    ner/nar sound<ctrl63>

    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
     Da
    0.48
    Da
    0.46
    avez
    0.46
    laden
    0.43
    遥
    0.41
    遙
    0.41
     دا
    0.40
    stud
    0.39
     da
    0.39
    da
    0.39
    POSITIVE LOGITS
     نار
    0.69
     नर
    0.66
    너
    0.65
    ner
    0.63
    ners
    0.63
     Nar
    0.62
    नर
    0.61
     nar
    0.61
    Nar
    0.59
    нер
    0.59
    Activations Density 0.004%

    No Known Activations