© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123326
    Prev
    Next
    INDEX
    Explanations

    sugar alcohol

    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_3_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
    I
    0.62
    ores
    0.61
    It
    0.60
    招标文件
    0.59
    ंना
    0.59
    ERS
    0.57
    ALE
    0.57
    ைட்
    0.57
    optosis
    0.57
    aines
    0.56
    POSITIVE LOGITS
    '
    1.21
     has
    0.79
    to
    0.72
     to
    0.71
    τή
    0.70
    ي
    0.69
    us
    0.68
    toare
    0.67
     can
    0.66
     had
    0.65
    Activations Density 0.000%

    No Known Activations