© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50988
    Prev
    Next
    INDEX
    Explanations

    meaning or sense

    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_31_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
    む
    0.35
    Voy
    0.34
     μ
    0.34
     различни
    0.34
     bombarded
    0.33
     ಆಗಿದೆ
    0.33
    єю
    0.33
    voy
    0.33
     υ
    0.32
     aute
    0.32
    POSITIVE LOGITS
     allowing
    0.37
     SEQUENCE
    0.37
    illez
    0.36
    clearInterval
    0.35
    getInstalled
    0.34
     memungkinkan
    0.34
     répon
    0.34
     إِن
    0.34
     étant
    0.33
     রাশ
    0.33
    Activations Density 0.103%

    No Known Activations