© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175610
    Prev
    Next
    INDEX
    Explanations

    POS tagging

    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_20_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
     सब्जियों
    0.45
    㢳
    0.42
    对称
    0.42
     जैसी
    0.40
     اجتما
    0.39
     Matlab
    0.39
     Symmetric
    0.38
     başına
    0.38
    "};
    0.38
     మె
    0.38
    POSITIVE LOGITS
     dominated
    0.50
     dominate
    0.49
     Dalib
    0.47
    Domin
    0.46
     domin
    0.45
     phon
    0.44
     دوم
    0.43
    Dal
    0.43
     refuted
    0.43
     ignored
    0.43
    Activations Density 0.001%

    No Known Activations