© 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
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 43903
    Prev
    Next
    INDEX
    Explanations

    length units (inches, cm)

    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_13_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
     Senate
    0.49
     mètres
    0.48
    ंखला
    0.48
     siège
    0.47
     balcony
    0.46
     "["
    0.45
     se
    0.45
     bait
    0.45
    ाये
    0.45
     reconnaît
    0.44
    POSITIVE LOGITS
     स्‍ट
    0.53
    Navigation
    0.52
    for
    0.50
    Micro
    0.50
    카
    0.50
    arrow
    0.50
    Faster
    0.50
    you
    0.49
    y
    0.49
    ph
    0.48
    Activations Density 0.012%

    No Known Activations