© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 207811
    Prev
    Next
    INDEX
    Explanations

    work on yourself or improving

    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
    '
    0.32
    incar
    0.28
    c
    0.27
    '।
    0.27
    mless
    0.26
    nicy
    0.26
    anigans
    0.26
     Seguro
    0.25
     travailleurs
    0.25
     않는
    0.25
    POSITIVE LOGITS
     of
    0.27
    一些
    0.26
    ట్స్‌మన్
    0.26
     叶
    0.25
    ية
    0.25
     我
    0.24
    颗粒
    0.24
    德
    0.24
    苷
    0.24
     or
    0.23
    Activations Density 0.002%

    No Known Activations