© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139261
    Prev
    Next
    INDEX
    Explanations

    distilled water

    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_12_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
     branche
    0.50
     groupe
    0.45
     lull
    0.45
     L
    0.45
    ทาง
    0.44
    Beschreibung
    0.44
    ฟัง
    0.43
    竑
    0.42
     strong
    0.42
     lignes
    0.42
    POSITIVE LOGITS
    isar
    0.59
    ositol
    0.55
    odar
    0.54
    oct
    0.53
    iserum
    0.52
    gä
    0.51
    agma
    0.50
    kün
    0.49
     acqua
    0.49
    лм
    0.48
    Activations Density 0.000%

    No Known Activations