© 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. 58430
    Prev
    Next
    INDEX
    Explanations

    walls

    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
     wall
    3.92
    Wall
    3.52
     Wall
    3.48
    wall
    3.41
     WALL
    3.28
    壁
    3.28
    WALL
    3.25
     벽
    3.05
     walls
    3.03
    벽
    2.92
    POSITIVE LOGITS
     vard
    0.37
    坤
    0.36
     স্ট্র
    0.35
    ิ้น
    0.34
    ruff
    0.33
     ತು
    0.33
    anguages
    0.33
    سة
    0.32
    ляется
    0.32
    ္
    0.32
    Activations Density 0.024%

    No Known Activations