© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26125
    Prev
    Next
    INDEX
    Explanations

    minimalist

    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_10_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
    ir
    0.99
    lu
    0.89
    し
    0.87
    ż
    0.82
    }")
    0.79
    ro
    0.78
    ع
    0.77
    ov
    0.77
    mer
    0.77
    sal
    0.76
    POSITIVE LOGITS
     minimalist
    0.77
    фан
    0.72
    اديم
    0.71
     quiver
    0.71
    垛
    0.71
     nove
    0.69
     minimal
    0.68
     minimalistic
    0.68
     hoard
    0.68
     encour
    0.66
    Activations Density 0.021%

    No Known Activations