© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14390
    Prev
    Next
    INDEX
    Explanations

    server endpoints, container aspects, moral judgment

    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_15_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
    ล
    0.53
    λώ
    0.52
     conjunction
    0.50
     gymnastics
    0.50
     functionality
    0.47
     detectors
    0.47
     cosmetics
    0.47
    λ
    0.47
     pendientes
    0.46
    ்
    0.46
    POSITIVE LOGITS
     தெரிவி
    0.64
    用地
    0.57
     бри
    0.55
     (\%)
    0.55
     सहमत
    0.55
    íguez
    0.55
     需要
    0.55
     您
    0.55
     જવાબ
    0.55
    吔
    0.54
    Activations Density 0.000%

    No Known Activations