© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 178038
    Prev
    Next
    INDEX
    Explanations

    royal places

    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
     Hercegov
    0.47
    тке
    0.42
     JOSE
    0.42
    ເກ
    0.38
    胝
    0.38
    埌
    0.38
    KERN
    0.38
     hören
    0.38
    hence
    0.37
    เก
    0.37
    POSITIVE LOGITS
    ชัน
    0.43
     Rey
    0.38
     představ
    0.38
    (".")
    0.38
     radial
    0.37
     Murphy
    0.37
     vanishing
    0.37
     Chester
    0.37
     chair
    0.37
    侵
    0.37
    Activations Density 0.004%

    No Known Activations