© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138120
    Prev
    Next
    INDEX
    Explanations

    user interface, interactions

    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
    security
    0.54
    Americans
    0.53
    0
    0.52
    Occasionally
    0.51
    আল
    0.50
    profession
    0.50
     ел
    0.50
    Aren
    0.50
    র্ষণ
    0.50
    Mve
    0.49
    POSITIVE LOGITS
    ovat
    0.55
     desarrollando
    0.51
     đa
    0.50
     STOP
    0.48
     esperado
    0.47
     SAI
    0.47
    癀
    0.46
    ございます
    0.46
     Segu
    0.46
     SA
    0.46
    Activations Density 0.001%

    No Known Activations