© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210783
    Prev
    Next
    INDEX
    Explanations

    lux followed by light or perpetua

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_5_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
    дования
    0.54
    fifty
    0.52
    াচার
    0.52
    causes
    0.52
    चारियों
    0.51
     ಈಗ
    0.50
     WENO
    0.50
    ),]),
    0.50
    doesn
    0.49
    ᡵ
    0.49
    POSITIVE LOGITS
    á
    0.89
    ä
    0.84
    ip
    0.72
    يل
    0.68
    ید
    0.66
    د
    0.64
    í
    0.64
    ó
    0.63
    ien
    0.62
    ig
    0.61
    Activations Density 0.000%

    No Known Activations