© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 150808
    Prev
    Next
    INDEX
    Explanations

    code and text

    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_59_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
     Wynne
    0.35
    出
    0.34
    uit
    0.33
     outer
    0.33
     Schne
    0.33
    못
    0.33
     ChromeDriver
    0.32
     Deserialize
    0.32
     Carne
    0.32
     quelqu
    0.32
    POSITIVE LOGITS
          
    0.57
           
    0.57
            
    0.57
    fungen
    0.46
    Son
    0.43
     maggio
    0.42
    Ù
    0.41
     акысыз
    0.41
    clear
    0.40
    ẋ
    0.40
    Activations Density 0.002%

    No Known Activations