© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 67527
    Prev
    Next
    INDEX
    Explanations

    german ID and tax regulations

    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_41_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
    out
    0.83
    ออก
    0.75
    Out
    0.74
    ອອກ
    0.68
     out
    0.67
    出
    0.66
    출
    0.66
     Out
    0.64
    出一
    0.64
     आउट
    0.59
    POSITIVE LOGITS
     Kala
    0.42
     mirrors
    0.41
    วล
    0.39
     nást
    0.39
    躏
    0.38
     PCT
    0.38
     mirror
    0.37
    tsy
    0.37
     cavalry
    0.37
    ennia
    0.37
    Activations Density 0.007%

    No Known Activations