© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 203738
    Prev
    Next
    INDEX
    Explanations

    space companies

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     pad
    0.43
    鋁
    0.42
     sap
    0.42
     chill
    0.38
     crane
    0.38
     cry
    0.38
     ais
    0.37
     ivy
    0.37
     Chill
    0.37
    丙
    0.37
    POSITIVE LOGITS
    maxx
    0.43
    Kernel
    0.42
    ೇಶ
    0.42
    主管部门
    0.40
    Conservation
    0.39
     One
    0.38
    Seconds
    0.38
    blox
    0.38
    ynet
    0.38
    コロ
    0.38
    Activations Density 0.002%

    No Known Activations