© 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. 32834
    Prev
    Next
    INDEX
    Explanations

    demonstration or demonstration-related actions

    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
    حديث
    0.39
     Sanz
    0.39
     comprar
    0.37
    msgSender
    0.37
     descans
    0.36
     boon
    0.35
     talking
    0.35
     정
    0.34
    キット
    0.34
     nghỉ
    0.34
    POSITIVE LOGITS
    演示
    0.74
     демонстра
    0.72
     Demonstration
    0.69
     demost
    0.68
     demonstrations
    0.67
     demonstration
    0.67
    demon
    0.64
     demonstra
    0.63
     demonstrate
    0.61
    Demon
    0.61
    Activations Density 0.048%

    No Known Activations