© 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. 2205
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to economic issues such as costs, prices, and family finances

    oai_token-act-pair · gemini-2.0-flash

    expenses and costs

    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
     متعلقه
    -0.69
    fortawesome
    -0.48
    qtt
    -0.44
    ']")
    -0.42
    HttpConnection
    -0.40
     Justice
    -0.39
    SBATCH
    -0.39
     чи
    -0.39
    elsif
    -0.39
    habe
    -0.38
    POSITIVE LOGITS
    EndInit
    0.72
    enumi
    0.67
     defStyle
    0.66
     setuptools
    0.60
    PyExc
    0.59
    </tfoot>
    0.58
     ویکی‌پدیای
    0.57
     مشارکت‌کنندگان
    0.57
    netbeans
    0.56
    OutputType
    0.56
    Activations Density 3.479%

    No Known Activations