© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 117195
    Prev
    Next
    INDEX
    Explanations

    trains, signaling, railway, railroad, transportation systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_38_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
    leigh
    0.39
    LIMIT
    0.39
     grills
    0.39
    ))`
    0.37
     ड्राइवर
    0.37
    इंटर
    0.36
    信号
    0.36
    框架
    0.36
     grilling
    0.36
     कैमरा
    0.36
    POSITIVE LOGITS
     Dion
    0.39
     вла
    0.37
    ຯ
    0.37
    плуа
    0.37
     ஆண்டுக
    0.37
     Ана
    0.37
     financial
    0.36
     absor
    0.36
    довле
    0.36
    صاف
    0.36
    Activations Density 0.008%

    No Known Activations