© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230717
    Prev
    Next
    INDEX
    Explanations

    pond words ending in "ond" or "ound"

    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_6_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
    ini
    0.79
    extremely
    0.73
    在
    0.72
     in
    0.71
    ent
    0.70
    p
    0.68
    ও
    0.66
    ก
    0.66
    ни
    0.65
    the
    0.65
    POSITIVE LOGITS
    ف
    1.19
    د
    0.84
    д
    0.82
    ق
    0.73
     señalado
    0.69
    بس
    0.68
    이스
    0.68
    ص
    0.67
    ਤੇ
    0.66
    ал
    0.66
    Activations Density 0.000%

    No Known Activations