© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 212793
    Prev
    Next
    INDEX
    Explanations

    dynamics

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    RJ
    0.50
     RJ
    0.46
    RANGER
    0.40
     árvore
    0.39
    ridos
    0.37
    स्
    0.36
    랜
    0.35
     ভো
    0.35
     Благо
    0.35
     amplifiers
    0.35
    POSITIVE LOGITS
     dynamics
    0.88
     Dynamics
    0.80
     динами
    0.77
     dynamic
    0.76
     dinam
    0.74
    Dynamics
    0.73
    dynamics
    0.71
    动态
    0.70
    Dynamic
    0.69
     dinámica
    0.69
    Activations Density 0.023%

    No Known Activations