© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 68544
    Prev
    Next
    INDEX
    Explanations

    satellite

    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
     нако
    0.39
    補
    0.39
     rectum
    0.38
     योगी
    0.38
     crawl
    0.37
     ከዚያ
    0.37
     हुन्छ
    0.36
     積
    0.36
     crawled
    0.36
     cor
    0.36
    POSITIVE LOGITS
     satellite
    1.87
    卫星
    1.71
     Satellite
    1.70
    Satellite
    1.67
    satellite
    1.66
    衛星
    1.55
     satell
    1.52
     satellites
    1.46
     спу
    1.21
     sat
    1.03
    Activations Density 0.001%

    No Known Activations