© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35743
    Prev
    Next
    INDEX
    Explanations

    political themes and governance

    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
    م
    1.20
    м
    0.97
    ب
    0.80
    เป็น
    0.75
    </h2>
    0.74
    ু
    0.73
    <0x0D>
    0.72
    ం
    0.71
    ı
    0.70
    ς
    0.70
    POSITIVE LOGITS
     پیچھے
    0.66
    apat
    0.65
    ಥವಾ
    0.60
    orn
    0.59
    কৃত
    0.59
    ভাগের
    0.59
    credible
    0.58
     Phương
    0.57
    benefit
    0.57
    và
    0.57
    Activations Density 0.025%

    No Known Activations