© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 235144
    Prev
    Next
    INDEX
    Explanations

    cities and countries

    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_46_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
     Kun
    0.59
    Kun
    0.52
     kun
    0.49
    勐
    0.48
    kun
    0.47
     Muse
    0.47
    瑞
    0.45
    昆
    0.44
     Meng
    0.42
     MUSE
    0.42
    POSITIVE LOGITS
    őt
    0.40
     ব্যাবস্থা
    0.37
    carpeta
    0.37
    быз
    0.37
    八
    0.37
    iev
    0.37
    addSql
    0.37
     নবী
    0.36
    obeb
    0.36
    ISM
    0.36
    Activations Density 0.006%

    No Known Activations