© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 203545
    Prev
    Next
    INDEX
    Explanations

    practice

    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_46_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
     kah
    0.41
    har
    0.41
     Enjoy
    0.40
     Хар
    0.39
     폐
    0.38
     işlet
    0.38
    Har
    0.38
    আনন্দ
    0.38
     Har
    0.37
     Autob
    0.37
    POSITIVE LOGITS
     practice
    0.50
     practicing
    0.49
     प्रैक्टिस
    0.46
     PRACTICE
    0.45
     prática
    0.44
     practising
    0.43
     práctica
    0.42
     practiced
    0.42
     pratica
    0.41
    
    0.41
    Activations Density 0.001%

    No Known Activations