© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140746
    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_12_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
    s
    0.59
    ы
    0.59
    ups
    0.57
    with
    0.54
    n
    0.53
    ía
    0.51
    using
    0.50
    ्स
    0.50
    ifs
    0.50
    *(
    0.50
    POSITIVE LOGITS
    AD
    0.66
    োজন
    0.57
     ṣ
    0.57
     faid
    0.56
     gele
    0.56
     treasure
    0.55
     trove
    0.55
     gă
    0.54
    VIDOR
    0.53
    SID
    0.52
    Activations Density 0.000%

    No Known Activations