© 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. 16502
    Prev
    Next
    INDEX
    Explanations

    property listings, seats, spaces

    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
    мії
    0.38
    "."
    0.36
    ссе
    0.35
    дино
    0.35
    碍
    0.35
    ګ
    0.34
     वॉल
    0.34
    ︾
    0.34
    étaire
    0.33
     المحدد
    0.33
    POSITIVE LOGITS
     seats
    0.55
     Seats
    0.55
     unoccupied
    0.55
    occupied
    0.52
    seats
    0.52
     vacant
    0.52
     আসন
    0.49
    Seats
    0.48
     occupied
    0.47
    席
    0.46
    Activations Density 0.049%

    No Known Activations