© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6483
    Prev
    Next
    INDEX
    Explanations

    phrases describing biological and chemical processes and interactions

    oai_token-act-pair · gemini-2.0-flash

    is/be

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     onCreateView
    -0.79
     виправивши
    -0.75
    DoubleQuotes
    -0.74
    IntoConstraints
    -0.70
    />";
    -0.69
    MigrationBuilder
    -0.69
     propOrder
    -0.69
    WebServlet
    -0.65
     nahilalakip
    -0.65
    IsContent
    -0.64
    POSITIVE LOGITS
    Rüyada
    0.63
    getOwner
    0.49
     konge
    0.48
     uñas
    0.47
    ayaquil
    0.47
     polymorphic
    0.46
    ClassLoader
    0.44
    zA
    0.44
     boyut
    0.43
     argint
    0.43
    Activations Density 3.475%

    No Known Activations