© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31722
    Prev
    Next
    INDEX
    Explanations

    Portuguese language

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     Sé
    0.89
    Sé
    0.88
    sé
    0.68
     Se
    0.63
     sé
    0.59
     Се
    0.57
    Se
    0.56
    é
    0.51
     се
    0.48
     Séance
    0.47
    POSITIVE LOGITS
    UI
    0.48
    ui
    0.47
    璟
    0.39
     પાર
    0.39
    いに
    0.37
    स्टर
    0.36
     pol
    0.36
     ui
    0.36
     sagitt
    0.36
     UI
    0.36
    Activations Density 0.008%

    No Known Activations