© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3614
    Prev
    Next
    INDEX
    Explanations

    technical descriptions of 3D displays and images

    oai_token-act-pair · gemini-2.0-flash

    terms related to "dimensional" concepts

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

    dimensionality

    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
     AssemblyTitle
    -0.64
    сылкі
    -0.57
     ویکی‌پدیای
    -0.55
    Билгалдахарш
    -0.50
     فريبيس
    -0.48
    PerformLayout
    -0.47
     <=",
    -0.46
    ="@+
    -0.45
    حياتها
    -0.45
    EUROPA
    -0.43
    POSITIVE LOGITS
    D
    1.40
    dimensional
    1.37
     dimensional
    1.36
     dimension
    1.34
     Dimension
    1.25
     Dimensional
    1.23
    Dimensional
    1.22
    dimension
    1.21
    Dimension
    1.15
     dimensions
    1.10
    Activations Density 2.758%

    No Known Activations