© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44061
    Prev
    Next
    INDEX
    Explanations

    Cape Flats accent, Good Hope, Capital Gain, FM

    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_3_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
     to
    0.77
    p
    0.66
     hypot
    0.61
    م
    0.61
     necessariamente
    0.60
    ↵↵
    0.60
     adot
    0.58
     Hilbert
    0.58
     arra
    0.58
     abelian
    0.57
    POSITIVE LOGITS
    сима
    0.70
    sorting
    0.69
    surf
    0.66
    ен
    0.65
    marginBottom
    0.64
    си
    0.63
    supreme
    0.63
    2
    0.63
    surfing
    0.62
    oh
    0.61
    Activations Density 0.001%

    No Known Activations