© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92176
    Prev
    Next
    INDEX
    Explanations

    Android Studio

    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_11_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
     classified
    0.25
    к
    0.25
    ᱠ
    0.24
    щу
    0.23
     medical
    0.23
    </h1>
    0.22
     covid
    0.22
    𝑘
    0.22
    QRSTUVWXYZ
    0.22
    covid
    0.22
    POSITIVE LOGITS
     паліты
    0.26
    <bos>
    0.26
     Japón
    0.25
     Италии
    0.25
     정치
    0.25
     Турции
    0.25
     السياسي
    0.24
    mato
    0.24
    gotoxy
    0.24
     polít
    0.24
    Activations Density 0.006%

    No Known Activations