© 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. 26941
    Prev
    Next
    INDEX
    Explanations

    SMART framework, FA Cup, Laser boats

    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
    Not in Any Lists

    No Comments

    Negative Logits
    antai
    0.39
     STARS
    0.38
    ⎛
    0.37
     Level
    0.37
     Lour
    0.37
     наде
    0.35
    ❿
    0.35
     hopes
    0.35
     BS
    0.35
     $('.
    0.35
    POSITIVE LOGITS
    CCNC
    0.44
    DUCTION
    0.36
    ricao
    0.35
    뚜
    0.34
     fibrils
    0.34
     infil
    0.33
     kuz
    0.33
    ޗ
    0.33
     kak
    0.33
     καθ
    0.33
    Activations Density 0.004%

    No Known Activations