© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 179406
    Prev
    Next
    INDEX
    Explanations

    year-over-year growth

    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_24_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
     Jazz
    0.43
     Caribbean
    0.41
    anesi
    0.41
    jazz
    0.39
     Ruch
    0.39
     }^{\
    0.39
     Vaz
    0.39
     Jaz
    0.39
    <0x9E>
    0.38
     vợ
    0.38
    POSITIVE LOGITS
    Sobre
    0.43
    UEL
    0.43
    OVER
    0.43
    られ
    0.42
    ড়িত
    0.42
    ABEL
    0.39
    ህል
    0.38
     ধু
    0.38
     PROJECTS
    0.38
    スタ
    0.38
    Activations Density 0.001%

    No Known Activations