© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 146901
    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_59_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
    的所有
    0.37
     ሁለት
    0.36
    wok
    0.35
    univ
    0.35
    所有
    0.35
     でしょう
    0.34
    EventManager
    0.34
     ኤ
    0.34
    得意
    0.33
    ۣ
    0.33
    POSITIVE LOGITS
     Ter
    0.61
     I
    0.61
    Ter
    0.55
     IUser
    0.49
     Terence
    0.48
     ter
    0.47
     terre
    0.45
     star
    0.45
     Terra
    0.45
     Peu
    0.45
    Activations Density 0.000%

    No Known Activations