© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 32092
    Prev
    Next
    INDEX
    Explanations

    Arabic suffixes / conjunctions

    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_7_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
    ä
    1.24
    я
    0.99
    на
    0.98
    ка
    0.85
    0.81
    z
    0.79
    </h3>
    0.79
    のことを
    0.77
    า
    0.77
     will
    0.77
    POSITIVE LOGITS
    지
    0.95
    inchi
    0.93
    ין
    0.90
     Fonbet
    0.89
    amax
    0.89
     quantos
    0.89
    트
    0.89
    adau
    0.87
     ကျွန်
    0.87
    udarstvennyj
    0.85
    Activations Density 0.000%

    No Known Activations