© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2677
    Prev
    Next
    INDEX
    Explanations

    words starting with "con"

    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_39_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
    baa
    0.40
    izzato
    0.38
     utilize
    0.37
     igreja
    0.37
     auxiliary
    0.36
    agedy
    0.36
    шк
    0.36
    뷁
    0.36
     पूर्वानु
    0.36
    illés
    0.35
    POSITIVE LOGITS
     コン
    0.73
    コン
    0.63
     Constantine
    0.62
     Constance
    0.61
    คอน
    0.61
    Кон
    0.60
     Кон
    0.60
     Константи
    0.60
     Congressional
    0.57
     Konstantin
    0.57
    Activations Density 0.086%

    No Known Activations