© 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. 127903
    Prev
    Next
    INDEX
    Explanations

    medication / icate endings

    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
    ة
    0.79
    ing
    0.68
    IS
    0.65
    有很多
    0.64
     Exodus
    0.63
     l
    0.63
    ového
    0.63
     histor
    0.61
    ిన
    0.60
    జర్
    0.60
    POSITIVE LOGITS
    1
    1.01
    اری
    0.87
    2
    0.84
    ین
    0.82
    preferences
    0.78
    ‌های
    0.77
     as
    0.77
     quisquam
    0.76
     умови
    0.75
    ется
    0.74
    Activations Density 0.001%

    No Known Activations