© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 35889
    Prev
    Next
    INDEX
    Explanations

    tree

    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
     तीनों
    0.84
    Triple
    0.80
     trinity
    0.76
     triple
    0.75
     三
    0.74
     ट्रिपल
    0.73
    三重
    0.73
     مثلث
    0.73
    的三
    0.72
     tripartite
    0.72
    POSITIVE LOGITS
     tree
    0.78
     Tree
    0.78
    tree
    0.74
    ee
    0.72
    ée
    0.67
    Tree
    0.66
    樹
    0.65
     TREE
    0.64
    ree
    0.63
     árbol
    0.63
    Activations Density 0.019%

    No Known Activations