© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 206222
    Prev
    Next
    INDEX
    Explanations

    names and ranks

    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_46_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
    rás
    0.48
     Naval
    0.40
    军队
    0.39
     Shil
    0.38
    Armor
    0.38
    盾
    0.38
     военных
    0.37
     Armor
    0.36
     Militar
    0.36
    hu
    0.36
    POSITIVE LOGITS
     beant
    0.43
    FileInputExcel
    0.42
     ছই
    0.40
    lyPlugin
    0.39
     reconhecimento
    0.39
    athar
    0.39
     করির
    0.38
    ɟ
    0.38
    harvard
    0.38
     credibility
    0.37
    Activations Density 0.000%

    No Known Activations