© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8206
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Normdatei
    -0.73
     EconPapers
    -0.61
    AsUp
    -0.56
    ulipas
    -0.56
    kloped
    -0.55
    Jeografia
    -0.55
    ttino
    -0.52
     configureStore
    -0.50
     noqa
    -0.50
     noDo
    -0.50
    POSITIVE LOGITS
     avoient
    0.65
     Capacidad
    0.60
     Letras
    0.60
     Tamanho
    0.60
     Acción
    0.59
     Informações
    0.58
     Nuevas
    0.58
     Ordem
    0.58
     Ejercicio
    0.58
     étoit
    0.57
    Activations Density 7.444%

    No Known Activations