© 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. 32093
    Prev
    Next
    INDEX
    Explanations

    code or data representations

    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
    f
    1.34
    F
    1.29
     f
    1.06
    ฟ
    1.01
    ｆ
    0.92
    EF
    0.91
    ف
    0.90
    Fs
    0.89
    ফ
    0.89
    yf
    0.89
    POSITIVE LOGITS
     FTA
    0.54
     फडण
    0.49
     FAA
    0.49
     FAU
    0.48
     FI
    0.46
     الفي
    0.46
     FDI
    0.46
     藤
    0.45
     FPGA
    0.45
    FAA
    0.44
    Activations Density 0.016%

    No Known Activations