© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 213620
    Prev
    Next
    INDEX
    Explanations

    nature and weather

    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_43_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
     meandering
    0.68
     sprawling
    0.68
     stretches
    0.58
     swaying
    0.57
    lush
    0.57
     majestic
    0.57
     lush
    0.56
    蜿
    0.56
     glist
    0.55
     glistening
    0.55
    POSITIVE LOGITS
     डिल
    0.39
     अभिकथन
    0.39
     edge
    0.39
     engage
    0.38
    iglie
    0.38
     substance
    0.37
     cục
    0.37
     telegram
    0.37
     torn
    0.36
     invested
    0.36
    Activations Density 0.174%

    No Known Activations