© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 241343
    Prev
    Next
    INDEX
    Explanations

    mountainous regions and plateaus

    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_40_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
     plains
    1.52
     plain
    1.51
    Plain
    1.44
     Plain
    1.41
    plain
    1.38
     Plains
    1.20
    平
    1.18
     lowland
    1.17
     flat
    1.09
     valley
    1.05
    POSITIVE LOGITS
     തൂ
    0.37
     dplyr
    0.37
    enum
    0.37
     shrugged
    0.37
     onRouteChange
    0.37
     enum
    0.36
    ഭ്യാസ
    0.36
    érien
    0.35
    ｉ
    0.35
     rugged
    0.35
    Activations Density 0.026%

    No Known Activations