© 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. 214308
    Prev
    Next
    INDEX
    Explanations

    Virtual

    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
    診
    0.38
     fundamentally
    0.37
    ][/
    0.35
    위에
    0.34
    arkan
    0.34
    ิ่ง
    0.33
    WAYS
    0.33
    촌
    0.33
     scopes
    0.32
     conceptually
    0.32
    POSITIVE LOGITS
     "),
    0.42
     pie
    0.40
     cro
    0.39
    Pie
    0.39
     pais
    0.38
    Sic
    0.37
     promover
    0.37
     لگ
    0.36
     victorious
    0.36
     exhaustive
    0.36
    Activations Density 0.002%

    No Known Activations