© 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. 29885
    Prev
    Next
    INDEX
    Explanations

    Rust keywords and types

    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
    arjo
    0.36
     RF
    0.35
     Commissioners
    0.35
     SAR
    0.34
    EQU
    0.33
     Cisco
    0.33
    RF
    0.33
     Robust
    0.32
    ធ
    0.32
     FT
    0.32
    POSITIVE LOGITS
     আলাই
    0.45
    plicator
    0.39
    roidery
    0.39
    人形
    0.38
    堵
    0.38
    ニング
    0.38
     perine
    0.38
    сай
    0.37
     opérés
    0.37
    脛
    0.37
    Activations Density 0.001%

    No Known Activations