© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 37049
    Prev
    Next
    INDEX
    Explanations

    too much

    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_31_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
     বিচারের
    0.35
    െയ
    0.34
     طاقت
    0.32
     سیا
    0.31
     aix
    0.30
    맟
    0.30
     Connecting
    0.29
    عبة
    0.28
     But
    0.28
     七
    0.28
    POSITIVE LOGITS
    putable
    0.32
    йно
    0.29
    льга
    0.28
     unquestionably
    0.28
    cribable
    0.28
    ณ์
    0.28
    rotechn
    0.28
    signal
    0.27
    ционного
    0.27
    Finite
    0.27
    Activations Density 0.010%

    No Known Activations