© 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. 178837
    Prev
    Next
    INDEX
    Explanations

    Fort

    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
    ıcı
    0.41
     js
    0.38
    涷
    0.38
     ರಾಜ
    0.37
    pyrimidine
    0.37
    ยอด
    0.37
     đẹp
    0.37
     Le
    0.36
     khaki
    0.36
    cco
    0.36
    POSITIVE LOGITS
     infr
    0.42
     prompted
    0.40
    মানিক
    0.40
    supervised
    0.38
    షు
    0.38
     equiv
    0.38
    myLabels
    0.38
    鏨
    0.38
    Toc
    0.37
     苏
    0.37
    Activations Density 0.001%

    No Known Activations