© 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. 156740
    Prev
    Next
    INDEX
    Explanations

    our

    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
    UCE
    0.39
    哥
    0.39
     गल
    0.38
    मोट
    0.38
    ರ್ಗ
    0.37
     Muff
    0.37
    ricos
    0.36
    عيب
    0.36
    },{
    0.36
    逓
    0.36
    POSITIVE LOGITS
    our
    1.25
    OUR
    1.24
    ours
    1.15
    oured
    1.08
    ouring
    1.02
    iour
    0.94
    oure
    0.93
    bour
    0.90
    Our
    0.88
    oura
    0.84
    Activations Density 0.002%

    No Known Activations