© 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. 137517
    Prev
    Next
    INDEX
    Explanations

    operating

    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
    ision
    0.40
     அழைத்து
    0.40
    ᓛ
    0.38
    IGA
    0.37
     వరు
    0.37
    preuve
    0.36
    system
    0.36
    NodeType
    0.36
     Informal
    0.36
     entitle
    0.35
    POSITIVE LOGITS
     fabricación
    0.43
     പ്രവർത്തന
    0.41
    ባቸው
    0.40
     مدل
    0.38
    模型的
    0.38
     cardio
    0.38
    模型
    0.38
     性
    0.37
     विधि
    0.37
    働き
    0.37
    Activations Density 0.002%

    No Known Activations