© 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
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 12108
    Prev
    Next
    INDEX
    Explanations

    civic engagement or virtue

    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_13_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
     tumbuhan
    0.20
     EtOH
    0.20
     ทุก
    0.20
     Fundación
    0.19
    ᱽ
    0.19
     Hazards
    0.18
     naciones
    0.18
     zaključ
    0.18
    ori
    0.18
     Wildlife
    0.18
    POSITIVE LOGITS
    دي
    0.18
    мо
    0.17
    www
    0.17
    bott
    0.17
    <0x98>
    0.17
    Morris
    0.17
     wallpaper
    0.16
    си
    0.16
    ште
    0.16
     keychain
    0.16
    Activations Density 0.021%

    No Known Activations