© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13654
    Prev
    Next
    INDEX
    Explanations

    labels for axes on a graph or plot, often involving "x" and "y"

    oai_token-act-pair · gemini-2.0-flash

    graph axes

    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
    出版年
    -0.90
     defaultstate
    -0.87
     مشين
    -0.81
    providedIn
    -0.79
    InjectAttribute
    -0.78
     nakalista
    -0.75
     ModelExpression
    -0.71
    IUrlHelper
    -0.69
    sizeCache
    -0.69
    ParallelGroup
    -0.68
    POSITIVE LOGITS
     judiciales
    0.44
    ase
    0.42
    犊
    0.42
    agon
    0.41
    PreInfinity
    0.41
     assi
    0.41
    IGNS
    0.41
     straight
    0.40
    мер
    0.39
    down
    0.39
    Activations Density 2.211%

    No Known Activations