© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 135059
    Prev
    Next
    INDEX
    Explanations

    words starting with Q or Qu

    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_37_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
    ეგისტრ
    0.41
    Cool
    0.40
    PrefabAsset
    0.39
    ඒ
    0.38
     Cie
    0.36
    hydraz
    0.36
     Cool
    0.36
     валю
    0.36
    lubridate
    0.36
    IZA
    0.35
    POSITIVE LOGITS
     Q
    0.55
     Qo
    0.54
     QQ
    0.51
     QSO
    0.49
     Quad
    0.48
    QQ
    0.48
     Quinn
    0.47
     QSOs
    0.46
     QP
    0.45
    Q
    0.45
    Activations Density 0.001%

    No Known Activations