© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12519
    Prev
    Next
    INDEX
    Explanations

    words that occur frequently in Danish movie titles

    oai_token-act-pair · 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
     I
    -0.47
     is
    -0.45
     van
    -0.43
     Ar
    -0.43
     et
    -0.43
    {}".
    -0.42
     how
    -0.42
     Dep
    -0.42
     der
    -0.41
    Ar
    -0.40
    POSITIVE LOGITS
    PreferredItem
    1.06
    verwijspagina
    0.87
    IUrlHelper
    0.81
    InSection
    0.77
     StatefulWidget
    0.75
    WebElementEntity
    0.70
    ReusableCell
    0.69
    BagLayout
    0.69
     StatelessWidget
    0.66
    InjectAttribute
    0.66
    Activations Density 0.668%

    No Known Activations