© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3488
    Prev
    Next
    INDEX
    Explanations

    language related to actions performed in the past

    oai_token-act-pair · gemini-2.0-flash

    location

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    DockStyle
    -0.88
     تضيفلها
    -0.81
     متعلقه
    -0.77
     كومونز
    -0.75
    viewDidLoad
    -0.72
     AttributeSet
    -0.69
     ExecuteAsync
    -0.69
    setupUi
    -0.69
    ReusableCell
    -0.68
     <<<<<<<<<<<<<<
    -0.65
    POSITIVE LOGITS
    reactstrap
    0.55
    shop
    0.47
     passada
    0.40
    trace
    0.40
     segre
    0.40
    }{#
    0.40
    RegressionTest
    0.40
    MS
    0.39
     khối
    0.39
     població
    0.39
    Activations Density 3.592%

    No Known Activations