© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12833
    Prev
    Next
    INDEX
    Explanations

    references to Danish history, titles, and locations, especially related to kings, dukes, and Schleswig-Holstein

    oai_token-act-pair · gemini-2.0-flash

    European nobility and geography

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    MigrationBuilder
    -0.66
    IntoConstraints
    -0.66
    oa̍t
    -0.63
    новниш
    -0.58
    })();
    -0.52
    alga
    -0.51
    Tikang
    -0.51
    Tembelea
    -0.49
    Diwedd
    -0.49
     Numerade
    -0.49
    POSITIVE LOGITS
    enumi
    0.67
    Javadoc
    0.52
    ViewFeatures
    0.46
    RectangleBorder
    0.45
    opy
    0.45
     notizia
    0.45
     kapak
    0.44
    testify
    0.43
    %)$
    0.43
     cappuccio
    0.43
    Activations Density 0.996%

    No Known Activations