© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3103
    Prev
    Next
    INDEX
    Explanations

    newline characters and numbers

    oai_token-act-pair · gemini-2.0-flash

    Repeated phrases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    RefNanny
    -0.63
    Portail
    -0.63
    webElement
    -0.59
    BuildContext
    -0.59
     pinulongan
    -0.57
    devamını
    -0.57
    Personendaten
    -0.56
     AssemblyCulture
    -0.54
    IBUS
    -0.52
    //
    -0.52
    POSITIVE LOGITS
     puissiez
    0.62
    GetEnumerator
    0.54
    ScopeManager
    0.53
    AddTagHelper
    0.52
    ViewImports
    0.50
     NSS
    0.49
    FieldBuilder
    0.48
    essica
    0.48
    ueux
    0.47
    uxxxx
    0.47
    Activations Density 0.918%

    No Known Activations