© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 162365
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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_31_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
     mistakes
    0.45
     Mistakes
    0.45
     apag
    0.41
     kesalahan
    0.40
     Multipart
    0.40
     잘못
    0.39
     Choices
    0.39
    
    0.39
     ایم
    0.38
     choices
    0.38
    POSITIVE LOGITS
    ylon
    0.43
    比例
    0.43
    floor
    0.42
    proportion
    0.40
     வசன
    0.38
     още
    0.38
    駁
    0.38
     console
    0.37
    还不
    0.37
     formed
    0.36
    Activations Density 0.001%

    No Known Activations