© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59701
    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_11_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
     역할
    0.55
    䢁
    0.53
     ভূম
    0.52
     Begriff
    0.50
    ༢
    0.49
    ༩
    0.48
    的能力
    0.48
    ۣ
    0.48
    薁
    0.47
     opér
    0.47
    POSITIVE LOGITS
     circumstantial
    0.51
     risk
    0.50
    हास
    0.50
    etat
    0.50
     map
    0.48
     fire
    0.48
     marriage
    0.48
     \
    0.47
    headed
    0.47
     genes
    0.47
    Activations Density 0.000%

    No Known Activations