© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36965
    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
     caminh
    0.54
    eppo
    0.52
     помога
    0.47
     propósito
    0.47
    ℑ
    0.46
     följande
    0.46
    𝕚
    0.46
     focusing
    0.46
     grooming
    0.45
     laboratorio
    0.45
    POSITIVE LOGITS
     Vorte
    0.53
     YORK
    0.45
    ր
    0.45
    armament
    0.43
    trends
    0.43
    으니
    0.43
     거지
    0.42
    IPLE
    0.42
    اق
    0.41
     DEJ
    0.41
    Activations Density 0.000%

    No Known Activations