© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2601
    Prev
    Next
    INDEX
    Explanations

    sentences about something coming to an end

    oai_token-act-pair · gemini-2.0-flash

    "to", beginning, ending

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    tigungs
    -0.56
    Sucesor
    -0.56
    onActivityResult
    -0.50
    DeleteBehavior
    -0.49
    macy
    -0.48
    ισ
    -0.47
    DropColumn
    -0.47
    
    -0.47
    Reco
    -0.46
    unhofer
    -0.46
    POSITIVE LOGITS
     nahilalakip
    0.62
    Демографія
    0.57
    tagHelperRunner
    0.57
    RectangleBorder
    0.57
    aarrggbb
    0.55
    ंदीखरीदारी
    0.54
     MainAxisSize
    0.52
    TableModel
    0.52
     invokingState
    0.52
     Biôgrafia
    0.50
    Activations Density 1.255%

    No Known Activations