© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9950
    Prev
    Next
    INDEX
    Explanations

    the word "ground" and words it commonly occurs near

    oai_token-act-pair · gemini-2.0-flash

    ground

    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
     peggio
    -0.55
     Grounds
    -0.48
     oeufs
    -0.47
     vPvB
    -0.47
     meisje
    -0.47
     Dara
    -0.46
    karakter
    -0.46
     değişti
    -0.46
     GROUND
    -0.46
    liferay
    -0.46
    POSITIVE LOGITS
    AddTagHelper
    0.79
     виправивши
    0.72
    MigrationBuilder
    0.71
    ftagPool
    0.71
     ligiloj
    0.70
    ,))
    0.69
    Rohy
    0.68
    AnchorStyles
    0.66
    ParallelGroup
    0.66
    featureID
    0.65
    Activations Density 1.436%

    No Known Activations