© 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. 90247
    Prev
    Next
    INDEX
    Explanations

    australian organizations and concepts

    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
    .
    0.63
     them
    0.56
     polymer
    0.55
    НО
    0.53
    ulat
    0.53
    一个小
    0.53
    iven
    0.52
     drink
    0.52
     बांट
    0.52
    ٨
    0.52
    POSITIVE LOGITS
    n
    0.94
    f
    0.89
    ו
    0.79
    و
    0.77
    ה
    0.77
    ק
    0.75
    on
    0.73
    ac
    0.66
    ต์
    0.66
    daki
    0.64
    Activations Density 0.000%

    No Known Activations