© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 64893
    Prev
    Next
    INDEX
    Explanations

    variable names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_51_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
     य
    0.48
    plin
    0.41
     postponed
    0.40
     refused
    0.39
    sortTable
    0.39
     י
    0.38
    ிகளின்
    0.37
     ی
    0.37
     توا
    0.37
    RequestBuilder
    0.37
    POSITIVE LOGITS
    HY
    0.84
     HY
    0.84
    GY
    0.82
     PY
    0.82
    SY
    0.82
     LY
    0.82
     JY
    0.82
    JY
    0.81
     SY
    0.79
    PY
    0.79
    Activations Density 0.012%

    No Known Activations