© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 99601
    Prev
    Next
    INDEX
    Explanations

    Renaissance centuries milestone booking ahead

    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_14_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
     :,
    0.54
     }:
    0.50
    ":
    0.47
     restrictions
    0.45
    :",
    0.45
     restricciones
    0.45
     provided
    0.45
     ",
    0.45
     vaut
    0.44
     Andover
    0.44
    POSITIVE LOGITS
    omitem
    0.59
    年后
    0.55
    ية
    0.53
    tan
    0.53
    ➖➖
    0.52
    eran
    0.52
    tem
    0.51
    تاجها
    0.50
    áním
    0.49
    ุ
    0.49
    Activations Density 0.000%

    No Known Activations