© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9049
    Prev
    Next
    INDEX
    Explanations

    property, registration, family matters

    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_40_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
     прогре
    0.39
    Progress
    0.39
    GLOB
    0.38
    eron
    0.38
    閣
    0.38
    odora
    0.37
    諸
    0.37
    ophile
    0.37
     progress
    0.37
    phil
    0.37
    POSITIVE LOGITS
    Properties
    0.41
    Utilization
    0.40
     Properties
    0.38
     رجسٹریشن
    0.38
    Ссы
    0.38
    webp
    0.37
    把握
    0.37
     proprietà
    0.37
    properties
    0.36
    ਢ
    0.36
    Activations Density 0.025%

    No Known Activations