© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50539
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
    釈
    0.60
    この
    0.58
    我
    0.55
     thisobject
    0.54
    toi
    0.54
     ढंग
    0.53
    ພວກເຮ
    0.53
    labeled
    0.53
     öğrenciler
    0.52
     પારિજા
    0.52
    POSITIVE LOGITS
     of
    0.63
     mobil
    0.57
     (
    0.54
     censure
    0.50
    er
    0.49
     media
    0.49
     capacité
    0.48
     system
    0.48
     volume
    0.47
     mobilisation
    0.47
    Activations Density 0.000%

    No Known Activations