© 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. 31433
    Prev
    Next
    INDEX
    Explanations

    mindfulness and calm

    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
    Sob
    0.40
    锥
    0.39
     Leinster
    0.39
     sob
    0.38
     enumerable
    0.38
    取消
    0.37
    dzi
    0.36
    LEGISLATIVE
    0.36
    Christopher
    0.36
     cytoplasmic
    0.35
    POSITIVE LOGITS
     Cas
    0.45
     Mic
    0.41
    Fcm
    0.39
     E
    0.38
    URANCE
    0.38
     अनार
    0.38
     Culture
    0.37
    cal
    0.37
     My
    0.36
    adar
    0.36
    Activations Density 0.001%

    No Known Activations