© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36901
    Prev
    Next
    INDEX
    Explanations

    ore and coal

    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_11_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
    Ꭶ
    0.54
     enero
    0.53
     "<<
    0.52
    ان
    0.51
    把握
    0.51
     (**
    0.49
    ور
    0.48
     oración
    0.48
    鯢
    0.48
     grasped
    0.47
    POSITIVE LOGITS
    ”-
    0.53
    kte
    0.50
    ।”
    0.48
    ”,
    0.48
    ETS
    0.47
    uacute
    0.46
     বন্দ্য
    0.46
     কৃষ্ণ
    0.46
    compile
    0.45
    nergie
    0.45
    Activations Density 0.015%

    No Known Activations