© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88389
    Prev
    Next
    INDEX
    Explanations

    jogar / jornada

    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
    i
    0.91
    י
    0.87
    ي
    0.82
    -
    0.78
    the
    0.75
    ா
    0.72
    ে
    0.71
     slot
    0.68
    ה
    0.68
    '
    0.67
    POSITIVE LOGITS
    렇게
    0.64
    াত্য
    0.63
    changer
    0.61
    hindi
    0.61
    entingan
    0.60
    BROW
    0.60
    PDE
    0.60
    UIManager
    0.59
    hlas
    0.59
    ड्यूल
    0.58
    Activations Density 0.002%

    No Known Activations