© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24787
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

    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_10_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
    t
    0.17
    ن
    0.14
    n
    0.13
    o
    0.12
    c
    0.12
    ت
    0.11
    an
    0.10
     Helper
    0.10
    /*
    0.10
    m
    0.10
    POSITIVE LOGITS
    ৫
    0.12
    し
    0.12
     lossless
    0.11
     heartbreaking
    0.11
    ᱕
    0.11
     букмекерлик
    0.11
    ५
    0.10
     နောက်
    0.10
     tên
    0.10
    buk
    0.10
    Activations Density 0.032%

    No Known Activations