© 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. 28845
    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
    鶚
    0.50
    勮
    0.46
    önt
    0.45
    щаем
    0.45
    ష్టం
    0.44
    ologija
    0.44
     саны
    0.44
     purnama
    0.44
    膂
    0.44
    鐗
    0.43
    POSITIVE LOGITS
    !
    0.61
     {
    0.50
    Â
    0.50
     receive
    0.50
    C
    0.49
     achieve
    0.49
     INTERNATIONAL
    0.49
     announced
    0.49
     identical
    0.48
    coordinate
    0.48
    Activations Density 0.000%

    No Known Activations