© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108627
    Prev
    Next
    INDEX
    Explanations

    'az' sound prefixes

    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_2_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
    ла
    1.52
    ם
    1.48
    ри
    1.43
    ים
    1.27
    ер
    1.21
    lar
    1.17
    лар
    1.15
    ล
    1.12
    িন
    1.09
    ом
    1.05
    POSITIVE LOGITS
    ج
    1.43
    n
    1.28
    ش
    1.24
    i
    1.05
    The
    1.02
    ij
    0.99
     substitu
    0.95
    P
    0.94
    C
    0.93
    j
    0.93
    Activations Density 0.001%

    No Known Activations