© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 62702
    Prev
    Next
    INDEX
    Explanations

    schaffen, schaffen, Schaffhausen

    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_2_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
    s
    1.77
    re
    1.44
    c
    1.31
    ter
    1.24
     as
    1.21
    ous
    1.21
    ren
    1.21
    am
    1.20
    ments
    1.20
    als
    1.16
    POSITIVE LOGITS
    ت
    1.46
     materiali
    1.24
    in
    1.16
     politici
    1.15
     prodotti
    1.10
    在北京
    1.09
     zakup
    1.08
    中国人
    1.08
    ہ
    1.08
    ו
    1.07
    Activations Density 0.000%

    No Known Activations