© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86916
    Prev
    Next
    INDEX
    Explanations

    tan... mais, não tão

    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_3_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
    ﻚ
    0.77
    ের
    0.75
     oraș
    0.75
    ка
    0.74
    renderCamera
    0.71
    centrum
    0.71
    ﻴ
    0.70
     रंजन
    0.69
    cią
    0.69
    lijke
    0.68
    POSITIVE LOGITS
    ع
    1.01
    م
    0.95
    ف
    0.91
    د
    0.87
    It
    0.84
    b
    0.79
    ó
    0.79
    س
    0.79
     It
    0.78
    ح
    0.77
    Activations Density 0.000%

    No Known Activations