© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2484
    Prev
    Next
    INDEX
    Explanations

    closing / closure

    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
    ObjectTemp
    0.43
    꾼
    0.36
    ammak
    0.35
    ונות
    0.35
     Auburn
    0.34
    꾸
    0.33
    panies
    0.33
    vii
    0.33
    ordelen
    0.33
    ⒉
    0.33
    POSITIVE LOGITS
     closure
    1.09
     closing
    1.08
     closes
    1.02
     Closing
    1.01
     Closure
    0.99
    Closing
    0.99
     clos
    0.98
     closures
    0.98
     закры
    0.96
     cierre
    0.95
    Activations Density 0.042%

    No Known Activations