© 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. 78994
    Prev
    Next
    INDEX
    Explanations

    Gom or соm

    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
    e
    1.91
    n
    1.75
    t
    1.69
    d
    1.57
    ت
    1.56
    o
    1.52
    on
    1.51
    et
    1.46
    ut
    1.45
    a
    1.42
    POSITIVE LOGITS
    و
    1.38
    ной
    1.35
    ام
    1.22
    ो
    1.19
    的外
    1.14
    的产品
    1.13
    的感觉
    1.13
    자
    1.09
    ка
    1.07
    的同时
    1.07
    Activations Density 0.000%

    No Known Activations