© 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. 91239
    Prev
    Next
    INDEX
    Explanations

    gathering information

    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
     manifesting
    0.61
    两
    0.58
     économ
    0.58
     гли
    0.56
     роботи
    0.54
    离
    0.54
     bursting
    0.53
     multiplicative
    0.53
    时间
    0.52
    лё
    0.52
    POSITIVE LOGITS
    amet
    0.67
    enfance
    0.66
    ين
    0.65
    ু
    0.64
    ul
    0.64
    ip
    0.63
    ak
    0.63
    am
    0.62
    z
    0.62
    ivet
    0.61
    Activations Density 0.003%

    No Known Activations