© 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. 91876
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ла
    0.95
    на
    0.79
    ные
    0.79
    ны
    0.75
    ها
    0.75
    いる
    0.70
    <0x0D>
    0.68
    ِ
    0.67
    রা
    0.66
    رم
    0.65
    POSITIVE LOGITS
     არ
    0.69
     שה
    0.67
     κά
    0.66
    K
    0.65
    N
    0.62
     earnest
    0.61
     በጣም
    0.61
     이미
    0.59
     αρχ
    0.59
    t
    0.58
    Activations Density 0.000%

    No Known Activations