© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 149968
    Prev
    Next
    INDEX
    Explanations

    word endings

    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_60_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
     ネ
    0.42
     ගැනීමට
    0.40
    স্ত্র
    0.40
     разбира
    0.40
     значения
    0.37
    いの
    0.37
     NE
    0.36
    डाय
    0.36
    قيم
    0.35
     بالق
    0.35
    POSITIVE LOGITS
    n
    2.34
    ni
    2.25
    ns
    2.09
    nes
    1.79
    nos
    1.78
    nis
    1.76
    nin
    1.66
    nál
    1.63
    nél
    1.62
    nies
    1.61
    Activations Density 0.054%

    No Known Activations