© 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. 36920
    Prev
    Next
    INDEX
    Explanations

    quick brown fox

    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
    g
    0.71
    .”.
    0.67
    are
    0.62
     промы
    0.62
     meromorphic
    0.62
     कामों
    0.61
     تعالى
    0.61
    ራሉ
    0.60
     слуша
    0.59
    .")
    0.59
    POSITIVE LOGITS
    ى
    0.89
    ב
    0.74
    ล
    0.72
    보
    0.71
    ת
    0.66
    </strong>
    0.63
    ם
    0.63
     you
    0.63
    드가
    0.62
    记
    0.62
    Activations Density 0.022%

    No Known Activations