© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 62395
    Prev
    Next
    INDEX
    Explanations

    square

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     house
    1.99
     home
    1.59
    家
    1.48
     House
    1.46
    house
    1.46
     घर
    1.45
    House
    1.40
    home
    1.34
    บ้าน
    1.33
     HOUSE
    1.32
    POSITIVE LOGITS
    Square
    0.48
     square
    0.47
     Square
    0.46
    平方
    0.46
    ‌ర
    0.45
     SQUARE
    0.44
     квадрат
    0.43
     वर्ग
    0.42
     sq
    0.42
     বর্গ
    0.42
    Activations Density 0.007%

    No Known Activations