© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11240
    Prev
    Next
    INDEX
    Explanations

    statements of clarity or establishment

    oai_token-act-pair · gemini-2.0-flash

    obvious

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    expandindo
    -0.83
     المعيارى
    -0.79
     Himo
    -0.69
     للاسماء
    -0.68
     kaarangay
    -0.68
     חיצוניים
    -0.67
    posób
    -0.66
     AssemblyProduct
    -0.65
     فريبيس
    -0.64
     SEDS
    -0.62
    POSITIVE LOGITS
     what
    0.90
     how
    0.83
    what
    0.78
     why
    0.75
     that
    0.71
    how
    0.71
    why
    0.69
     we
    0.68
     they
    0.63
     whether
    0.62
    Activations Density 4.196%

    No Known Activations