© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 106831
    Prev
    Next
    INDEX
    Explanations

    having followed by noun phrase

    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_2_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
    ح
    1.77
    ق
    1.37
    ف
    1.35
    ان
    1.32
    ק
    1.26
    ر
    1.22
    ير
    1.21
    ਾ
    1.21
    ม
    1.20
    א
    1.18
    POSITIVE LOGITS
    কে
    0.98
    க்கு
    0.93
    T
    0.93
    F
    0.89
    V
    0.86
    L
    0.85
    RA
    0.82
    W
    0.81
    >∕
    0.80
     encompass
    0.79
    Activations Density 0.001%

    No Known Activations