© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18480
    Prev
    Next
    INDEX
    Explanations

    warehouses and distribution centers

    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_15_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
    광
    0.52
    ξε
    0.51
     biskup
    0.51
    %).
    0.50
    H
    0.50
    둔
    0.49
    Just
    0.49
    신
    0.49
    COLUMN
    0.48
    عدد
    0.47
    POSITIVE LOGITS
     retouch
    0.53
    ancas
    0.53
     सात
    0.49
    énez
    0.48
    uasion
    0.48
    netje
    0.48
    modation
    0.47
     Buds
    0.46
    ivative
    0.46
    峣
    0.46
    Activations Density 0.002%

    No Known Activations