© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 196796
    Prev
    Next
    INDEX
    Explanations

    Types

    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_50_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
    ৃত
    0.38
    𝙘
    0.37
    懐
    0.36
     spineItem
    0.35
     ನಗರ
    0.34
    ())).
    0.34
    بوع
    0.34
    ካት
    0.34
    ყ
    0.34
     обще
    0.33
    POSITIVE LOGITS
     type
    0.99
     типа
    0.91
    type
    0.89
    Type
    0.80
     tipo
    0.79
     types
    0.79
     тип
    0.79
    类型
    0.78
     типу
    0.76
     TYPE
    0.74
    Activations Density 0.008%

    No Known Activations