© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37671
    Prev
    Next
    INDEX
    Explanations

    Wes Anderson, days, nights

    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
    り
    0.82
    も
    0.71
     och
    0.71
    д
    0.69
    전
    0.68
     detergents
    0.65
     thì
    0.65
    드는
    0.65
    쓸
    0.64
    스는
    0.64
    POSITIVE LOGITS
    انو
    0.64
    ن
    0.59
    st
    0.59
     Epis
    0.55
    buje
    0.55
    ง
    0.55
     цер
    0.53
    urization
    0.53
    bilir
    0.52
    uene
    0.51
    Activations Density 0.000%

    No Known Activations