© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 197219
    Prev
    Next
    INDEX
    Explanations

    attention with linear biases

    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_15_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
    onden
    0.66
    ignment
    0.53
    ima
    0.52
    ity
    0.51
    át
    0.51
    p
    0.51
    aining
    0.50
    mal
    0.50
    ito
    0.50
    mock
    0.49
    POSITIVE LOGITS
     Wallpaper
    0.64
    КП
    0.61
     Oficial
    0.59
     Pretoria
    0.59
     ',');
    0.58
     Bromley
    0.57
     Russie
    0.57
    錒
    0.56
    след
    0.56
     Werte
    0.56
    Activations Density 0.003%

    No Known Activations