© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 69073
    Prev
    Next
    INDEX
    Explanations

    Arizona

    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
     Qui
    0.41
    seo
    0.41
     rico
    0.40
    readonly
    0.39
    ClassLoader
    0.39
    quy
    0.39
    Qui
    0.38
    
    0.38
    .".,
    0.38
    adigan
    0.37
    POSITIVE LOGITS
     Metern
    0.40
     Baton
    0.39
     bat
    0.38
     управ
    0.38
     Plan
    0.38
    指数
    0.37
     Bat
    0.37
     इश्
    0.37
     Wool
    0.36
     Summer
    0.36
    Activations Density 0.001%

    No Known Activations