© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108311
    Prev
    Next
    INDEX
    Explanations

    Marines or mariners

    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_1_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
    '
    1.46
     potrebbero
    0.98
    AG
    0.97
     hóa
    0.96
    uje
    0.96
     clásico
    0.96
     chiam
    0.95
     creado
    0.94
    ۰
    0.94
     prema
    0.93
    POSITIVE LOGITS
    나
    1.45
    را
    1.44
    ری
    1.36
    ون
    1.32
    نا
    1.26
    ود
    1.24
    ни
    1.20
    ט
    1.18
    не
    1.14
    et
    1.13
    Activations Density 0.001%

    No Known Activations