© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84149
    Prev
    Next
    INDEX
    Explanations

    removing duplicates

    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_0_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
    ت
    1.66
    т
    1.63
    ات
    1.56
    t
    1.45
    ו
    1.42
    y
    1.34
    kans
    1.28
    ا
    1.24
    ی
    1.24
    kosten
    1.23
    POSITIVE LOGITS
    ن
    2.34
    น
    2.31
    ন
    1.91
    n
    1.89
    न
    1.84
    ン
    1.56
    した
    1.53
    ่
    1.52
    ều
    1.40
    नं
    1.39
    Activations Density 0.002%

    No Known Activations