© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19807
    Prev
    Next
    INDEX
    Explanations

    default

    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_15_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
    yb
    0.53
    ystate
    0.52
    utin
    0.46
    ly
    0.46
    ý
    0.44
    ysts
    0.44
    untamiento
    0.44
     challenges
    0.43
     threatening
    0.43
    ystring
    0.42
    POSITIVE LOGITS
    Dados
    0.45
    Leggi
    0.45
    Productos
    0.45
    제품
    0.44
    Diethyl
    0.44
    ווי
    0.43
    ইন্দ
    0.43
    ској
    0.42
     पंजीकृत
    0.41
    봇
    0.41
    Activations Density 0.009%

    No Known Activations