© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 30863
    Prev
    Next
    INDEX
    Explanations

    由 / ค่อย

    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_7_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
    ک
    0.92
     is
    0.88
    し
    0.86
     are
    0.83
    是
    0.82
    會
    0.78
    för
    0.76
    無い
    0.76
    য়ের
    0.75
    4
    0.75
    POSITIVE LOGITS
    et
    0.98
    at
    0.98
    ar
    0.93
    as
    0.79
     carbure
    0.79
     \
    0.78
    ו
    0.77
    د
    0.75
    рила
    0.75
    на
    0.74
    Activations Density 0.000%

    No Known Activations