© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 152162
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_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
     организм
    0.57
    Ⲑ
    0.56
     territorios
    0.52
    "।
    0.52
     Испа
    0.50
    पुरम
    0.50
     可愛
    0.50
    ウイルス
    0.50
     අනුව
    0.50
     ञ
    0.49
    POSITIVE LOGITS
    0.53
    To
    0.51
    Note
    0.43
    He
    0.42
    One
    0.42
    Governor
    0.41
    列表
    0.41
    toBottomOf
    0.41
    Let
    0.40
    Revenue
    0.40
    Activations Density 0.000%

    No Known Activations