© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53584
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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_55_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
    里
    0.77
     里
    0.70
    中
    0.65
     లో
    0.61
    裏
    0.59
    上
    0.58
    ում
    0.57
    里的
    0.57
    裡
    0.56
    种
    0.54
    POSITIVE LOGITS
    డంలో
    0.55
    鍦
    0.54
     पाण्यात
    0.53
    日本では
    0.52
     በእ
    0.51
    ობაში
    0.50
    在大
    0.50
    કામાં
    0.48
     በአ
    0.47
    所で
    0.47
    Activations Density 0.004%

    No Known Activations