© 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. 88634
    Prev
    Next
    INDEX
    Explanations

    worn out

    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
    iť
    0.71
    ে
    0.67
     Gdy
    0.66
    ｲ
    0.59
     Když
    0.59
    იც
    0.59
    ي
    0.59
    )।
    0.58
    ი
    0.58
    ו
    0.58
    POSITIVE LOGITS
    ation
    0.74
    ine
    0.61
     Rangers
    0.57
    ishing
    0.57
    ande
    0.56
     stren
    0.56
    t
    0.55
    ide
    0.55
    ulla
    0.54
    শিব
    0.54
    Activations Density 0.000%

    No Known Activations