© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40518
    Prev
    Next
    INDEX
    Explanations

    however small

    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_3_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
    et
    0.79
    il
    0.79
    ("
    0.73
    b
    0.68
    3
    0.67
    -
    0.64
     Were
    0.63
    w
    0.62
    ى
    0.61
    r
    0.59
    POSITIVE LOGITS
     لیګ
    0.94
     présentation
    0.76
     политики
    0.75
    اين
    0.75
     машиналары
    0.74
     لاءِ
    0.73
     ajoute
    0.72
     različ
    0.71
     пользователь
    0.71
     станда
    0.70
    Activations Density 0.001%

    No Known Activations