© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3736
    Prev
    Next
    INDEX
    Explanations

    hexadecimal strings, especially including those representing memory addresses or color codes

    oai_token-act-pair · gemini-2.0-flash

    hexadecimal code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    StructEnd
    -0.88
     فريبيس
    -0.79
    actionMode
    -0.75
     typelib
    -0.68
    ConstraintMaker
    -0.68
    GEBURTSDATUM
    -0.63
     BoxFit
    -0.62
    sizeCache
    -0.60
     المعيارى
    -0.60
    #
    -0.60
    POSITIVE LOGITS
     so
    0.52
     or
    0.48
    newtheorem
    0.47
    ffilm
    0.46
    ...
    0.45
    BindingSource
    0.43
     phénomène
    0.43
     meccan
    0.43
    たびに
    0.42
    촉
    0.42
    Activations Density 38.901%

    No Known Activations