© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91898
    Prev
    Next
    INDEX
    Explanations

    high kicks, industrialized, consensus

    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_3_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
     for
    0.93
     you
    0.76
     one
    0.70
    ش
    0.70
     conceptually
    0.66
     বিষয়টা
    0.66
     criticizing
    0.66
     exorbitant
    0.65
     renormalized
    0.64
     reasoned
    0.64
    POSITIVE LOGITS
    da
    0.84
    ’
    0.73
    ية
    0.71
    تها
    0.70
    ت
    0.70
    laut
    0.69
    der
    0.66
    ลูก
    0.66
    यों
    0.66
    h
    0.66
    Activations Density 0.002%

    No Known Activations