© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 205400
    Prev
    Next
    INDEX
    Explanations

    a certain

    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
    Negative Logits
    ק
    0.97
    ج
    0.92
     modific
    0.89
    ي
    0.88
     materia
    0.84
     qualific
    0.84
     months
    0.83
     divulg
    0.81
     pregi
    0.80
    म
    0.79
    POSITIVE LOGITS
    ano
    0.80
    ator
    0.72
    tering
    0.71
    ter
    0.70
    rivers
    0.70
    assadors
    0.69
    lective
    0.69
    ler
    0.67
    enz
    0.67
    rah
    0.66
    Activations Density 0.003%

    No Known Activations