© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 223156
    Prev
    Next
    INDEX
    Explanations

    centrally located

    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_10_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
    '
    0.86
    -
    0.81
     envi
    0.72
    ↵
    0.70
    ;
    0.68
     தெரிவித்தனர்
    0.67
    ]
    0.67
     $\
    0.66
     MM
    0.66
    \
    0.66
    POSITIVE LOGITS
     спорттук
    0.77
    健身
    0.65
    ز
    0.64
     kendini
    0.63
     ক্রিকেটার
    0.63
     наші
    0.63
    बाल
    0.62
    ждая
    0.62
     можем
    0.61
    其他
    0.60
    Activations Density 0.000%

    No Known Activations