© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19676
    Prev
    Next
    INDEX
    Explanations

    HDMI, SD, MMC, Lua

    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_15_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
     alloy
    0.49
     पत
    0.49
     Arjuna
    0.49
     बर्तन
    0.48
     eficaz
    0.48
    perg
    0.48
     airflow
    0.47
    r
    0.47
     apparatus
    0.47
    หลาย
    0.46
    POSITIVE LOGITS
    нде
    0.53
     Camero
    0.49
    comments
    0.48
    Commands
    0.47
     মাহ
    0.47
    Termination
    0.47
    Ｎ
    0.47
    Interrupt
    0.47
    Rename
    0.47
    Written
    0.47
    Activations Density 0.022%

    No Known Activations