© 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. 113444
    Prev
    Next
    INDEX
    Explanations

    pixie, pixar, pixabay

    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
    ية
    1.92
    在
    1.20
    ير
    1.14
    ání
    1.11
    కు
    1.04
    يد
    1.02
    َ
    0.98
    ának
    0.97
    ление
    0.94
    里
    0.94
    POSITIVE LOGITS
    ิ
    1.42
    i
    1.33
    י
    1.33
    w
    1.18
    ק
    1.11
    רים
    1.09
    ac
    1.08
    <0x0D>
    1.06
     Europeans
    1.06
    க்கொள்ள
    1.06
    Activations Density 0.000%

    No Known Activations