© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 64922
    Prev
    Next
    INDEX
    Explanations

    su

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_51_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
     meadow
    0.44
    ܂
    0.44
     пра
    0.43
     Пра
    0.41
     Meadow
    0.40
     meadows
    0.39
     Andrews
    0.38
    മേ
    0.38
     prairies
    0.38
     并
    0.37
    POSITIVE LOGITS
    <0x89>
    0.45
    пление
    0.42
    P
    0.42
    吾
    0.41
    Pol
    0.41
    ポリ
    0.41
    บั
    0.39
    𝙿
    0.39
    <0x85>
    0.39
    pol
    0.38
    Activations Density 0.000%

    No Known Activations