© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54774
    Prev
    Next
    INDEX
    Explanations

    linking libraries like SQLite, llama, ML, Oracle

    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_30_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
     trusses
    0.25
     عمران
    0.24
     Plattform
    0.24
    ಮಾಣ
    0.23
    ன்னா
    0.23
     अभिया
    0.23
     왼
    0.23
     заб
    0.22
    arius
    0.22
     wir
    0.22
    POSITIVE LOGITS
    ോദ
    0.26
    dió
    0.25
    Ordering
    0.25
     pixels
    0.24
    olerance
    0.24
    orphic
    0.24
    þ
    0.24
    톡
    0.24
    ichi
    0.24
    ensitivity
    0.24
    Activations Density 0.005%

    No Known Activations