© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 252252
    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
    obes
    0.39
    鵃
    0.39
     EDUC
    0.38
     वॉ
    0.37
     दैट
    0.36
     المؤمن
    0.36
     விடு
    0.36
     educativo
    0.36
     PAPER
    0.36
    edu
    0.36
    POSITIVE LOGITS
     wavelength
    2.23
     wavelengths
    1.95
    wavelength
    1.95
    avelength
    1.17
    lambda
    0.93
     lambda
    0.87
     λ
    0.84
    λ
    0.83
    𝜆
    0.70
    yarn
    0.67
    Activations Density 0.001%

    No Known Activations