© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 15056
    Prev
    Next
    INDEX
    Explanations

    blood vessels

    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_34_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
    enzo
    0.37
     Forecast
    0.36
    isser
    0.36
    enite
    0.35
     Abu
    0.35
    oods
    0.35
    糞
    0.35
    脲
    0.35
     metformin
    0.34
     Dolphins
    0.34
    POSITIVE LOGITS
     vessels
    0.71
     capillaries
    0.69
     Vessels
    0.66
     vaisseaux
    0.65
    血管
    0.65
     VESSELS
    0.63
     vessel
    0.60
     capillary
    0.60
     vasculature
    0.60
     bleed
    0.56
    Activations Density 0.050%

    No Known Activations