© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12278
    Prev
    Next
    INDEX
    Explanations

    the German word "und," which means "and."

    oai_token-act-pair · gemini-2.0-flash

    und

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     und
    -2.56
     Und
    -1.70
    Und
    -1.63
    und
    -1.59
     UND
    -1.32
    UND
    -1.19
     oder
    -0.90
     undec
    -0.79
    undi
    -0.79
    unda
    -0.79
    POSITIVE LOGITS
     ویکی‌پدی
    0.71
     >=",
    0.69
     виправивши
    0.68
    XmlAccessType
    0.67
    oredCriteria
    0.63
     nahilalakip
    0.63
     rigide
    0.63
     humains
    0.61
    Autoritní
    0.61
    ">//
    0.60
    Activations Density 0.695%

    No Known Activations