© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 183910
    Prev
    Next
    INDEX
    Explanations

    What do you enjoy

    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_29_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
     কারণে
    0.37
     आगामी
    0.37
     détermine
    0.36
    ㏄
    0.36
     данном
    0.36
    /**
    0.35
    并非
    0.35
    amblea
    0.35
    过于
    0.35
    ირო
    0.35
    POSITIVE LOGITS
     Gamma
    0.38
     favorably
    0.37
     legjob
    0.37
     خۆ
    0.36
    峽
    0.36
     ці
    0.35
    support
    0.35
     favourably
    0.35
    支持
    0.34
    born
    0.34
    Activations Density 0.013%

    No Known Activations