© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18079
    Prev
    Next
    INDEX
    Explanations

    technical skills or difficulty

    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_40_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
     Murn
    0.39
    ন্দ
    0.38
    чется
    0.37
     intramuscular
    0.33
    くまで
    0.33
     Nahrung
    0.32
     miserable
    0.32
    嫩
    0.32
     শাস্ত
    0.32
     []);
    0.32
    POSITIVE LOGITS
     technical
    2.16
    technical
    2.03
    Technical
    2.02
     Technical
    1.94
    TECHNICAL
    1.88
     TECHNICAL
    1.85
     техни
    1.77
     टेक्निकल
    1.69
     технических
    1.66
     technischen
    1.63
    Activations Density 0.256%

    No Known Activations