© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 199916
    Prev
    Next
    INDEX
    Explanations

    medical procedures techniques employing

    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_9_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
    t
    0.75
     are
    0.67
    0.59
    inį
    0.58
    swith
    0.56
    I
    0.56
    ף
    0.55
    Ia
    0.53
     as
    0.52
    וף
    0.51
    POSITIVE LOGITS
    ;
    0.76
    ie
    0.74
    aklar
    0.67
    ptidase
    0.63
     ও
    0.62
    ak
    0.62
     ವಿಧಾನಸ
    0.61
     riche
    0.59
     GAMMA
    0.59
     अनंत
    0.59
    Activations Density 0.001%

    No Known Activations