© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 66593
    Prev
    Next
    INDEX
    Explanations

    numerical lists

    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_51_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
       
    0.35
    廟
    0.34
    0.33
      
    0.32
    ho
    0.32
     *
    0.31
     spell
    0.31
     jump
    0.30
     mornings
    0.29
     Minist
    0.29
    POSITIVE LOGITS
     duyg
    0.39
    Dess
    0.39
    
    0.37
    MSFont
    0.37
     फोर
    0.36
    लिसा
    0.35
     শুক্রাচার্য
    0.35
    ěn
    0.35
    荥
    0.35
     चाहर
    0.35
    Activations Density 0.006%

    No Known Activations