© 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
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 980
    Prev
    Next
    INDEX
    Explanations

    data tables with numerical values (measurements) and related characteristics

    oai_token-act-pair · gemini-2.0-flash

    tables of numerical data

    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
    mirante
    -0.51
    !("{}",
    -0.48
     organizations
    -0.46
    ptes
    -0.43
     organization
    -0.43
     moment
    -0.42
    interceptors
    -0.41
    URIComponent
    -0.41
     Schumacher
    -0.41
    getElementById
    -0.41
    POSITIVE LOGITS
     Réponses
    0.85
    Personendaten
    0.83
    msgTypes
    0.71
    XmlAccessType
    0.69
     resourceCulture
    0.68
    webElementGuid
    0.68
     ModelExpression
    0.65
    FunctionFlags
    0.63
    Хьажоргаш
    0.63
    Vidite
    0.63
    Activations Density 3.674%

    No Known Activations