© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 193439
    Prev
    Next
    INDEX
    Explanations

    if/else conditionals

    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_9_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
    ación
    0.85
    ind
    0.84
    ется
    0.84
     друго
    0.84
    s
    0.84
    在
    0.84
    ی
    0.81
    ";
    0.81
     άλλο
    0.81
    ing
    0.80
    POSITIVE LOGITS
     to
    1.04
     or
    0.79
     \
    0.75
    to
    0.73
    ian
    0.73
    ب
    0.72
    း
    0.71
    ia
    0.71
    ید
    0.70
    에
    0.70
    Activations Density 0.037%

    No Known Activations