© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 128892
    Prev
    Next
    INDEX
    Explanations

    én plus me/bě/hé

    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_1_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
    <0x91>
    1.09
    <0xA8>
    1.05
    اني
    1.05
    স
    1.02
    น
    1.02
    не
    1.01
    <0x98>
    0.98
    أ
    0.95
     slew
    0.93
    <0xAC>
    0.92
    POSITIVE LOGITS
    t
    1.86
    し
    1.19
    ties
    1.06
    tive
    1.03
     of
    1.02
    ions
    1.02
    ियों
    1.02
    cı
    1.02
    ä
    1.02
    یس
    0.98
    Activations Density 0.001%

    No Known Activations