© 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. 234965
    Prev
    Next
    INDEX
    Explanations

    magnetism and materials

    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
     magnetic
    3.36
    Magnetic
    3.16
    磁
    3.16
     Magnetic
    3.13
    magnetic
    3.13
     магнит
    2.97
     MAGNETIC
    2.83
     magnet
    2.80
     magnétique
    2.64
     magnetism
    2.61
    POSITIVE LOGITS
     chickens
    0.39
    ਲੀ
    0.38
     poultry
    0.37
     বোর্ড
    0.37
     Mythology
    0.35
    🍗
    0.35
     greed
    0.35
    Pasta
    0.35
     Muller
    0.35
    Myers
    0.35
    Activations Density 0.013%

    No Known Activations