© 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. 12047
    Prev
    Next
    INDEX
    Explanations

    university domain names and research centers

    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
     sólo
    0.42
    ين
    0.41
    穷
    0.38
    罣
    0.37
     dimensiones
    0.36
    薔
    0.36
    ゲーム
    0.36
    导航
    0.35
    <0x80>
    0.35
    щает
    0.34
    POSITIVE LOGITS
    ISM
    0.44
    LeftSide
    0.42
    ﺐ
    0.42
    (${
    0.39
     hyperemia
    0.38
    విద్య
    0.38
    =${
    0.38
    PS
    0.38
    EDS
    0.38
     Biochim
    0.38
    Activations Density 0.020%

    No Known Activations