© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 233027
    Prev
    Next
    INDEX
    Explanations

    ticks

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     tille
    0.72
     tincture
    0.64
     tiller
    0.62
     ти
    0.60
     티
    0.60
     til
    0.59
     t
    0.59
     T
    0.58
     ტი
    0.58
     tij
    0.56
    POSITIVE LOGITS
     клави
    0.43
    keydown
    0.39
    键盘
    0.39
     блоки
    0.39
    ่อน
    0.38
     филосо
    0.37
     Keyboard
    0.36
     поку
    0.36
    符号
    0.35
     ब्लॉक
    0.35
    Activations Density 0.003%

    No Known Activations