© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199825
    Prev
    Next
    INDEX
    Explanations

    the movie Matrix

    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_12_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
    V
    0.54
    انگ
    0.48
    <0x0D>
    0.47
    সমান
    0.47
     précision
    0.46
    NOV
    0.45
    nue
    0.45
     américains
    0.45
    spers
    0.45
    EXECUT
    0.45
    POSITIVE LOGITS
     was
    0.44
     विश्वास
    0.42
    ールの
    0.40
     ሃ
    0.40
    }`}
    0.40
     rä
    0.39
     quiescent
    0.39
    ѓ
    0.39
     ㅜ
    0.39
    rag
    0.38
    Activations Density 0.001%

    No Known Activations