© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115225
    Prev
    Next
    INDEX
    Explanations

    performance-based fees

    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_27_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
    ifi
    0.32
     Booklet
    0.28
     deteriorated
    0.26
    ief
    0.26
    .”
    0.26
    mar
    0.25
    ochet
    0.25
    ;
    0.25
     Years
    0.25
    ;'
    0.25
    POSITIVE LOGITS
     इन्वेस्टमेंट
    0.35
     regalías
    0.34
    鏻
    0.33
    顴
    0.33
    费用
    0.32
    शेखर
    0.32
     سرمایہ
    0.32
    鉀
    0.31
     HOSP
    0.31
    క్కు
    0.30
    Activations Density 0.003%

    No Known Activations