© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44915
    Prev
    Next
    INDEX
    Explanations

    chain, beta, delta subunits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_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
     यूनिवर्स
    0.60
    produktion
    0.57
    纽约
    0.54
     효과
    0.54
    midrule
    0.53
    🆈
    0.52
     ////
    0.52
     ಯಾವಾಗ
    0.52
     buoyancy
    0.51
    এশিয়া
    0.51
    POSITIVE LOGITS
    o
    0.64
    í
    0.52
     É
    0.52
    e
    0.52
    TP
    0.49
    É
    0.49
    E
    0.48
    al
    0.47
    fr
    0.47
     diem
    0.47
    Activations Density 0.001%

    No Known Activations