© 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. 137789
    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
    8
    0.63
    4
    0.59
    6
    0.57
     patents
    0.57
    rying
    0.54
    5
    0.54
    وم
    0.54
    leyen
    0.54
     SISO
    0.54
     richt
    0.53
    POSITIVE LOGITS
    नई
    0.62
     errone
    0.61
    มัน
    0.58
    ል
    0.57
     یې
    0.57
    お店
    0.56
     litre
    0.56
     iu
    0.56
    น้ำ
    0.54
     nỗi
    0.54
    Activations Density 0.000%

    No Known Activations