© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14299
    Prev
    Next
    INDEX
    Explanations

    parliamentary bodies and representatives

    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
    is
    0.70
    use
    0.66
    {
    0.64
    ta
    0.58
     about
    0.57
    est
    0.56
    age
    0.54
    ung
    0.54
    B
    0.54
    used
    0.53
    POSITIVE LOGITS
    蹼
    0.60
     للمعارف
    0.58
     усили
    0.55
     igjen
    0.54
     bicovariant
    0.54
     vielleicht
    0.52
     Elovl
    0.52
     ಥ
    0.52
     llrp
    0.52
     glLightfv
    0.51
    Activations Density 0.000%

    No Known Activations