© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 142280
    Prev
    Next
    INDEX
    Explanations

    critically,

    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_12_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ר
    0.69
    ر
    0.69
    ك
    0.67
     one
    0.62
     l
    0.61
    কাতা
    0.58
     LQ
    0.57
    ي
    0.55
    اري
    0.55
     NCBI
    0.55
    POSITIVE LOGITS
    pyrazine
    0.59
    astes
    0.54
     combustibles
    0.54
    -
    0.53
    achten
    0.52
    onden
    0.50
    ಟ್‌
    0.50
     plantings
    0.49
    _
    0.48
    arton
    0.47
    Activations Density 0.004%

    No Known Activations