© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6083
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to graph theory and statistical modeling

    oai_token-act-pair · gemini-2.0-flash

    theory

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     BorderRadius
    -0.78
    ArgsConstructor
    -0.72
    WebControls
    -0.68
    BagConstraints
    -0.67
     بيها
    -0.66
     незавершена
    -0.63
    Portale
    -0.62
    بوابة
    -0.62
    RTDA
    -0.61
    MENAFN
    -0.60
    POSITIVE LOGITS
     theory
    0.65
     Theory
    0.62
    WriteLiteral
    0.54
     theoretical
    0.54
     THEORY
    0.52
    Theory
    0.52
    theory
    0.52
     Theorie
    0.52
     teor
    0.50
     teoria
    0.50
    Activations Density 2.763%

    No Known Activations