© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 203408
    Prev
    Next
    INDEX
    Explanations

    line segment

    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_12_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
    ።
    0.18
    arii
    0.15
     सप्टेंबर
    0.14
    ۔
    0.14
    .*
    0.14
    .<
    0.14
    .(
    0.14
    .";
    0.13
    trä
    0.13
     दिसते
    0.13
    POSITIVE LOGITS
     MILLER
    0.16
     Miller
    0.15
    ﺭ
    0.14
    is
    0.14
     ABC
    0.14
     malice
    0.13
    க்கே
    0.13
    ר
    0.13
     CFO
    0.13
     интерес
    0.13
    Activations Density 0.000%

    No Known Activations