© 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. 31651
    Prev
    Next
    INDEX
    Explanations

    che

    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
     kerja
    0.42
    宵
    0.40
    дено
    0.39
    Lov
    0.39
    azas
    0.39
    лость
    0.38
     broch
    0.37
    ljivo
    0.37
    韆
    0.37
    ਿਆ
    0.37
    POSITIVE LOGITS
    ousing
    0.42
    тып
    0.38
    émy
    0.38
    unken
    0.37
     Myr
    0.37
     Dow
    0.37
    ålet
    0.37
    ameron
    0.36
     स्वर्
    0.36
     elt
    0.36
    Activations Density 0.001%

    No Known Activations