© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 215331
    Prev
    Next
    INDEX
    Explanations

    idle

    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_47_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
     працю
    0.39
    
    0.39
     تعمل
    0.39
    SNR
    0.38
    ఠ
    0.38
     ユ
    0.37
    处理器
    0.37
     Trabal
    0.37
     travailler
    0.37
    working
    0.36
    POSITIVE LOGITS
     Clip
    0.42
     Cam
    0.39
     Hodge
    0.38
    φό
    0.37
    pciones
    0.37
    hatian
    0.36
     ballast
    0.36
    Configs
    0.35
    缥
    0.35
     Assist
    0.35
    Activations Density 0.001%

    No Known Activations