© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14545
    Prev
    Next
    INDEX
    Explanations

    lead generation and marketing

    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_13_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
    的服务
    0.51
     Planetary
    0.49
    ashington
    0.48
     planetary
    0.48
    agues
    0.48
    गेड
    0.48
    CONFIG
    0.47
    床
    0.47
    服務
    0.47
     ওয়ার
    0.46
    POSITIVE LOGITS
    куляр
    0.52
     ouvertes
    0.52
    зма
    0.49
     постоян
    0.49
     cupr
    0.49
     mald
    0.48
    м
    0.48
    цы
    0.47
     immisc
    0.47
    баров
    0.46
    Activations Density 0.065%

    No Known Activations