© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8979
    Prev
    Next
    INDEX
    Explanations

    words related to saving money and resources

    oai_token-act-pair · gemini-2.0-flash

    references to saving or money

    np_token-act-pair-logits · gpt-4o-mini

    save

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    webElementXpaths
    -0.58
    PointerException
    -0.54
    TypedArray
    -0.45
    RegistryLite
    -0.45
    igeon
    -0.45
    relief
    -0.45
     Relief
    -0.44
    Javadoc
    -0.42
    omiast
    -0.42
    Relief
    -0.42
    POSITIVE LOGITS
     Administrativna
    0.65
    ыгана
    0.65
    tshire
    0.61
     ویکی‌پدیا
    0.60
     للاسماء
    0.60
     Chwiliwch
    0.57
     AssemblyTitle
    0.56
     <=",
    0.56
     مواليد
    0.55
     ujednoznacz
    0.55
    Activations Density 7.112%

    No Known Activations