© 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. 133811
    Prev
    Next
    INDEX
    Explanations

    HELP

    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
     छाप
    0.36
     puas
    0.35
     moat
    0.35
     Rico
    0.35
    verläss
    0.35
    चारियों
    0.35
    weh
    0.35
     %>',
    0.35
    heap
    0.35
    ức
    0.34
    POSITIVE LOGITS
     Kamil
    0.50
    ZF
    0.43
    pleClass
    0.42
    ZX
    0.41
    MyToolkit
    0.40
    Asian
    0.40
    Телефон
    0.39
    鑾
    0.39
    CENTER
    0.38
     Tul
    0.38
    Activations Density 0.001%

    No Known Activations