© 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. 158201
    Prev
    Next
    INDEX
    Explanations

    proper nouns, MRN

    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
    칭
    0.44
     Hamiltonian
    0.42
     М
    0.41
    罕
    0.41
     M
    0.41
    ె
    0.41
    Hamilton
    0.38
     K
    0.38
    ईडी
    0.38
     দক্ষি
    0.38
    POSITIVE LOGITS
     Cain
    0.40
    Yah
    0.39
    stal
    0.39
     belles
    0.38
    kag
    0.38
     اله
    0.37
     Yah
    0.37
    BLO
    0.37
     बायो
    0.37
    vag
    0.37
    Activations Density 0.008%

    No Known Activations