© 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. 11913
    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
     старо
    0.55
    center
    0.53
    cafe
    0.53
     démon
    0.52
    okee
    0.50
    pose
    0.50
    학년
    0.49
    ᆫ
    0.49
    hairs
    0.48
    DA
    0.48
    POSITIVE LOGITS
     də
    0.55
     Penal
    0.53
     Wild
    0.52
     interrupting
    0.49
     Bel
    0.49
    ゲーム
    0.49
     infecting
    0.49
     ゲーム
    0.48
     Twenty
    0.48
     behaviours
    0.48
    Activations Density 0.000%

    No Known Activations