© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 196268
    Prev
    Next
    INDEX
    Explanations

    complex concepts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    并
    1.14
    並
    0.98
     并
    0.95
    และ
    0.92
     और
    0.89
     και
    0.86
     ແລະ
    0.86
     и
    0.86
     và
    0.86
     এবং
    0.84
    POSITIVE LOGITS
     ontwikkelen
    0.37
    చె
    0.35
     नामक
    0.35
     သည်
    0.35
    ڈنگ
    0.34
    是在
    0.33
    ften
    0.33
     nonché
    0.33
    іб
    0.32
    رحبا
    0.32
    Activations Density 0.079%

    No Known Activations