© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43847
    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_13_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
     váy
    0.52
    ချက်
    0.50
    akkam
    0.49
    ب
    0.49
    ava
    0.48
    ೊಂದ
    0.47
    ovable
    0.46
    PDO
    0.46
    ieva
    0.46
     robotics
    0.46
    POSITIVE LOGITS
    σεων
    0.58
    bandingan
    0.55
    y
    0.52
    Switzerland
    0.51
    驄
    0.49
     ширина
    0.48
    див
    0.48
     зала
    0.48
    ｼ
    0.48
    σεις
    0.47
    Activations Density 0.000%

    No Known Activations