© 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. 10418
    Prev
    Next
    INDEX
    Explanations

    code-like text, especially that related to layouts, controls, and UI elements

    oai_token-act-pair · gemini-2.0-flash

    Programming syntax

    np_max-act-logits · 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
    __':
    -0.76
    verwijspagina
    -0.72
     مرئيه
    -0.71
     defaultstate
    -0.70
     nakalista
    -0.68
     ostavi
    -0.66
    LEncoder
    -0.63
    __":
    -0.59
    MemoryWarning
    -0.58
     disambiguazione
    -0.58
    POSITIVE LOGITS
    projeto
    0.62
    mensaje
    0.62
    proyecto
    0.59
    resposta
    0.58
    telefono
    0.58
    pessoa
    0.57
    plantilla
    0.57
    contenido
    0.56
    produtos
    0.56
    contacto
    0.56
    Activations Density 10.758%

    No Known Activations