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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124613
    Prev
    Next
    INDEX
    Explanations

    government centers graphics street market

    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_3_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
    น
    0.79
    н
    0.77
    ン
    0.77
     of
    0.76
     that
    0.74
     ́
    0.72
    holders
    0.71
    ’
    0.68
    that
    0.66
    \'
    0.65
    POSITIVE LOGITS
    espère
    0.67
     сложи
    0.66
    ৫
    0.64
     supprimer
    0.64
    وم
    0.63
    eded
    0.63
     reconoc
    0.62
     chercher
    0.62
     pú
    0.62
    jourd
    0.61
    Activations Density 0.064%

    No Known Activations