© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 146509
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_18_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
    多く
    0.50
    ПУ
    0.50
    miri
    0.48
    Greece
    0.47
    Europe
    0.45
    RNN
    0.45
    銀
    0.45
    innovation
    0.45
    وير
    0.45
    ت
    0.45
    POSITIVE LOGITS
     chế
    0.49
    喷
    0.48
     आय
    0.47
     kệ
    0.46
     حاض
    0.45
     बगल
    0.45
     Спа
    0.43
     COMPONENTS
    0.43
     RATE
    0.42
     एंड
    0.42
    Activations Density 0.000%

    No Known Activations