© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219678
    Prev
    Next
    INDEX
    Explanations

    green and its qualities

    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_31_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
     winter
    0.83
    winter
    0.72
     winters
    0.71
     invierno
    0.67
     겨울
    0.66
     सर्दियों
    0.66
     vinter
    0.65
    冬
    0.65
    Winter
    0.62
    冬季
    0.61
    POSITIVE LOGITS
    Machine
    0.39
     Incub
    0.39
     সার্ভ
    0.39
     Machines
    0.38
     मशीन
    0.38
    pH
    0.38
    Máy
    0.36
    
    0.36
     המח
    0.36
    nT
    0.36
    Activations Density 0.001%

    No Known Activations