© 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. 90921
    Prev
    Next
    INDEX
    Explanations

    **plus / ensuite / suspend**

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    斯
    0.67
    ক্স
    0.64
    스
    0.60
    اس
    0.59
    のス
    0.57
    س
    0.57
    Vik
    0.56
    ס
    0.56
    Wol
    0.54
    സ്
    0.54
    POSITIVE LOGITS
    ение
    0.55
    выми
    0.55
    षी
    0.55
     millón
    0.55
     metabolite
    0.54
     combating
    0.54
     unaltered
    0.54
    élev
    0.54
    ила
    0.53
    ваете
    0.53
    Activations Density 0.000%

    No Known Activations