© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133989
    Prev
    Next
    INDEX
    Explanations

    perspective

    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
    Not in Any Lists

    No Comments

    Negative Logits
    0
    1.13
    t
    1.10
    h
    1.05
    den
    1.02
    лини
    0.98
    ри
    0.96
    al
    0.95
    erie
    0.94
    อร์
    0.92
    ek
    0.91
    POSITIVE LOGITS
    ج
    1.61
    ق
    1.59
    ص
    1.53
    ين
    1.41
     to
    1.41
    ם
    1.39
    회
    1.32
    ס
    1.30
     be
    1.28
    פ
    1.25
    Activations Density 0.002%

    No Known Activations