© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58113
    Prev
    Next
    INDEX
    Explanations

    **intensive** posterior probability

    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_11_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
    bahan
    0.59
     ఏర్ప
    0.55
    areas
    0.54
    тации
    0.54
    viewer
    0.54
    硏
    0.54
    endaftaran
    0.54
    ುತ್ತದೆ
    0.53
    ボン
    0.53
    ন্ত্রণ
    0.52
    POSITIVE LOGITS
     i
    0.61
     congress
    0.55
     hvilket
    0.54
     paroles
    0.53
     happiest
    0.52
     spool
    0.52
    EndOf
    0.52
     $
    0.51
     Number
    0.50
     opcode
    0.49
    Activations Density 0.026%

    No Known Activations