© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 200661
    Prev
    Next
    INDEX
    Explanations

    corners

    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_50_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
    ⁴
    0.39
    ierten
    0.36
    ₁(
    0.36
     はい
    0.36
    டையே
    0.35
    ౪
    0.35
    程度上
    0.34
     než
    0.34
    ABL
    0.34
     four
    0.33
    POSITIVE LOGITS
    ঠা
    0.47
     corners
    0.42
    ⿰
    0.40
    corners
    0.39
     quadrants
    0.39
    tene
    0.38
    zet
    0.38
    ẩn
    0.38
     corner
    0.37
    corner
    0.37
    Activations Density 0.012%

    No Known Activations