© 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. 214921
    Prev
    Next
    INDEX
    Explanations

    origin explaining words

    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
     Fence
    0.28
     обре
    0.28
    矚
    0.28
    fill
    0.28
    maks
    0.27
     prvo
    0.27
    录
    0.27
    早い
    0.27
    mapSize
    0.26
    झा
    0.26
    POSITIVE LOGITS
     coffin
    0.34
    日曜
    0.33
    ంతో
    0.32
     হোক
    0.31
     सिविल
    0.31
    ovania
    0.31
    ϋ
    0.30
     สืบค้นเมื่อ
    0.30
     cholest
    0.29
    ayena
    0.29
    Activations Density 0.001%

    No Known Activations