© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 49544
    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_10_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
     distract
    0.54
     Assemble
    0.52
     mono
    0.48
     stor
    0.48
     δ
    0.47
     puff
    0.47
     wrap
    0.46
     donut
    0.45
     testing
    0.45
     Muay
    0.45
    POSITIVE LOGITS
    ็อก
    0.51
    Packages
    0.50
    Actress
    0.49
    恶
    0.49
    Poems
    0.47
    Due
    0.46
    IAL
    0.46
    ድግዳ
    0.46
    开放
    0.45
    uisine
    0.45
    Activations Density 0.000%

    No Known Activations