© 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. 65462
    Prev
    Next
    INDEX
    Explanations

    bind

    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
     binding
    0.91
     Binding
    0.88
    Binding
    0.79
    binding
    0.77
     bindings
    0.71
    綁
    0.68
     Bind
    0.65
    绑定
    0.62
    绑
    0.59
     bind
    0.58
    POSITIVE LOGITS
     hunted
    0.46
    ipy
    0.42
     naik
    0.41
     plantation
    0.39
     وړ
    0.39
     gali
    0.39
    AddModel
    0.39
    Direction
    0.39
    input
    0.38
    InputField
    0.38
    Activations Density 0.002%

    No Known Activations