© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20935
    Prev
    Next
    INDEX
    Explanations

    fencing

    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_56_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
     fence
    0.98
    fence
    0.91
    Fence
    0.88
     Fence
    0.83
     fences
    0.81
     fencing
    0.74
     fenced
    0.71
    柵
    0.49
     огра
    0.48
     hedge
    0.43
    POSITIVE LOGITS
     F
    2.20
     f
    2.09
     ফ
    1.88
     फ
    1.84
    f
    1.67
     ف
    1.65
    F
    1.62
    ฟ
    1.49
     ฟ
    1.47
     الف
    1.44
    Activations Density 0.017%

    No Known Activations