© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 102709
    Prev
    Next
    INDEX
    Explanations

    requires, demands, applies

    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_1_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
    é
    1.29
    f
    1.28
     botas
    1.09
     commence
    1.08
    ي
    1.08
     បាន
    1.07
     طبي
    1.06
    ين
    1.05
     comportamenti
    1.05
     can
    1.04
    POSITIVE LOGITS
    3
    1.33
    4
    1.23
    ری
    1.16
    را
    1.13
    ہ
    1.05
    lation
    1.02
    یم
    1.02
    아
    1.02
    riere
    0.97
    راک
    0.96
    Activations Density 0.001%

    No Known Activations