© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 60462
    Prev
    Next
    INDEX
    Explanations

    intertw

    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_59_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
     intertwined
    1.85
     entw
    1.75
     intertw
    1.73
     interwoven
    1.41
     entangled
    1.20
     entanglement
    1.14
     inextricably
    0.87
    缠
    0.83
     intre
    0.67
     inextric
    0.57
    POSITIVE LOGITS
    tw
    0.89
     tw
    0.80
    ine
    0.63
    TW
    0.63
    Tw
    0.58
    ined
    0.56
    w
    0.56
     inex
    0.54
     TW
    0.53
     пере
    0.51
    Activations Density 0.099%

    No Known Activations