© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 34905
    Prev
    Next
    INDEX
    Explanations

    hosting foreign dignitaries or events

    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_11_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
     δεδο
    0.57
     EPFO
    0.53
    antly
    0.53
    ngth
    0.53
     reorgan
    0.53
     ремо
    0.52
     enanti
    0.52
    ;
    0.51
    ays
    0.51
    acking
    0.51
    POSITIVE LOGITS
    ര്‍
    0.66
    Lion
    0.64
    Star
    0.62
     thịt
    0.62
    中
    0.61
    тері
    0.61
    ين
    0.60
    zón
    0.60
    merken
    0.60
    測試
    0.59
    Activations Density 0.000%

    No Known Activations