© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9894
    Prev
    Next
    INDEX
    Explanations

    words and phrases one might find in a description of a wrestling match, particularly scores and periods

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     transfieras
    -0.77
    ViewFeatures
    -0.77
     AssemblyCompany
    -0.60
     елның
    -0.58
    Diweddarwch
    -0.55
    usercontent
    -0.54
    UnitTesting
    -0.54
     Ferdinando
    -0.54
    SharedCtor
    -0.53
    basti
    -0.52
    POSITIVE LOGITS
    tvguidetime
    0.62
    AutoresizingMask
    0.55
     initComponents
    0.50
    modb
    0.48
     vandal
    0.47
    kwds
    0.47
     join
    0.47
    Zitat
    0.46
    درب
    0.45
     open
    0.45
    Activations Density 0.781%

    No Known Activations