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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 100747
    Prev
    Next
    INDEX
    Explanations

    request, reference, deadline, processes

    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_16_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
    Jets
    0.44
    зи
    0.44
    Fusion
    0.40
    ਂ
    0.39
    aje
    0.38
    drawable
    0.38
     trouvait
    0.38
     translational
    0.38
    SOD
    0.38
    garten
    0.38
    POSITIVE LOGITS
    with
    0.60
     prawn
    0.53
    ជាមួយ
    0.53
     velik
    0.51
     mög
    0.51
     Ü
    0.50
     kapas
    0.50
     deteriorate
    0.49
     പിന്ന
    0.49
     capac
    0.48
    Activations Density 0.000%

    No Known Activations