© 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. 156413
    Prev
    Next
    INDEX
    Explanations

    parts of names

    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
     a
    1.25
    ak
    1.00
    ية
    0.97
    O
    0.96
    eta
    0.96
    0
    0.95
    ang
    0.94
     is
    0.93
     on
    0.93
    ay
    0.93
    POSITIVE LOGITS
    ي
    1.19
    s
    1.16
     agreg
    1.09
    t
    1.05
    一部分
    0.98
     mecánica
    0.97
    י
    0.97
     refleja
    0.96
     частью
    0.96
    אן
    0.95
    Activations Density 0.002%

    No Known Activations