© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43993
    Prev
    Next
    INDEX
    Explanations

    write out

    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_3_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
     I
    0.76
    d
    0.64
     racem
    0.63
    k
    0.62
    c
    0.62
    kör
    0.61
     diminish
    0.61
    kých
    0.61
     कॉनक
    0.59
     Thanos
    0.58
    POSITIVE LOGITS
    س
    0.85
    。
    0.69
    ية
    0.65
    0.65
    с
    0.64
    یم
    0.64
    。</
    0.64
    بة
    0.63
    ف
    0.63
    ناع
    0.63
    Activations Density 0.003%

    No Known Activations