© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21617
    Prev
    Next
    INDEX
    Explanations

    wavelength

    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_56_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
     wavelength
    2.47
    wavelength
    2.19
     wavelengths
    2.17
    avelength
    1.38
    lambda
    0.96
    λ
    0.87
     lambda
    0.85
     λ
    0.84
     yarn
    0.78
     wavenumber
    0.77
    POSITIVE LOGITS
    ర్వాత
    0.41
     EDUC
    0.41
    obes
    0.40
    hib
    0.40
    edu
    0.39
     المؤمن
    0.39
     mous
    0.38
     Lordships
    0.37
     Emory
    0.37
    Educ
    0.36
    Activations Density 0.019%

    No Known Activations