© 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. 42247
    Prev
    Next
    INDEX
    Explanations

    Mary Had a Little Lamb

    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
    J
    0.64
    ت
    0.62
    ك
    0.61
    но
    0.59
    {
    0.58
    ق
    0.58
    ة
    0.56
    身上
    0.55
    yní
    0.55
    膈
    0.54
    POSITIVE LOGITS
    s
    0.79
    in
    0.71
     in
    0.71
    r
    0.66
    t
    0.65
    st
    0.65
     infix
    0.64
    n
    0.61
    towards
    0.58
    l
    0.58
    Activations Density 0.000%

    No Known Activations