© 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-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11536
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to art, artistry, and artistic techniques.

    oai_token-act-pair · gemini-2.0-flash

    art installations and percentages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    vikle
    -0.52
     onFailure
    -0.51
     Unders
    -0.50
     بيها
    -0.50
    arpa
    -0.49
    igil
    -0.47
    cmath
    -0.47
    featureID
    -0.46
     Closer
    -0.46
    onAttach
    -0.46
    POSITIVE LOGITS
     propOrder
    0.89
    rungsseite
    0.74
     незавершена
    0.68
    mybatisplus
    0.63
    BagConstraints
    0.63
    NameInMap
    0.63
    oa̍t
    0.62
     disambiguazione
    0.60
     uintptr
    0.59
    JspWriter
    0.56
    Activations Density 8.965%

    No Known Activations