© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 127308
    Prev
    Next
    INDEX
    Explanations

    ship container

    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_37_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
     fleet
    0.62
     fleets
    0.54
    fleet
    0.54
     sailing
    0.46
    ⛵
    0.46
     transports
    0.44
     traveling
    0.44
    Fleet
    0.44
     marine
    0.43
     transportation
    0.42
    POSITIVE LOGITS
    CONTAIN
    0.52
     contenedor
    0.42
    ئے۔
    0.41
    濁
    0.41
    容器
    0.40
     CONTAINER
    0.40
    浊
    0.40
     Reservoir
    0.40
     Container
    0.38
    avacanam
    0.38
    Activations Density 0.002%

    No Known Activations