© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11459
    Prev
    Next
    INDEX
    Explanations

    historical writing utilizing archaic pronouns and dates

    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
    ulipas
    -0.53
    subpackage
    -0.47
    .‏
    -0.47
     الحره
    -0.46
    PointerException
    -0.45
    illoma
    -0.44
    RectangleBorder
    -0.44
    Vorlage
    -0.43
     gigante
    -0.43
     corpor
    -0.42
    POSITIVE LOGITS
    oredCriteria
    0.81
    TagMode
    0.74
    GraphicsUnit
    0.63
    XmlEnum
    0.62
     урна
    0.60
    Geografi
    0.59
     Paglinawan
    0.59
     tramonto
    0.59
    Personensuche
    0.58
    reportWebVitals
    0.58
    Activations Density 2.515%

    No Known Activations