© 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. 200961
    Prev
    Next
    INDEX
    Explanations

    seats

    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
    pathi
    0.36
    ὠ
    0.35
     examine
    0.35
     Mares
    0.35
     Analyze
    0.35
     kak
    0.34
     lòng
    0.34
     Examine
    0.34
     Grounds
    0.34
     Recht
    0.34
    POSITIVE LOGITS
     seated
    0.86
     seating
    0.80
    座
    0.79
     seats
    0.77
     座
    0.76
    앉
    0.73
     seat
    0.73
    seated
    0.73
     siège
    0.71
     sentado
    0.71
    Activations Density 0.000%

    No Known Activations