© 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. 41162
    Prev
    Next
    INDEX
    Explanations

    modularity, modifications, modesty, modest, modicum

    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
    8
    0.84
    7
    0.81
    5
    0.79
    (
    0.76
    6
    0.75
    در
    0.72
    9
    0.70
     time
    0.70
    ،
    0.70
    \
    0.69
    POSITIVE LOGITS
     efficacement
    0.63
     Hfn
    0.62
     avrà
    0.61
    gdock
    0.56
    <unused4>
    0.55
     geen
    0.55
     αρχ
    0.55
    '>"
    0.55
     diligently
    0.55
     UNNEEDED
    0.54
    Activations Density 0.002%

    No Known Activations