© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2584
    Prev
    Next
    INDEX
    Explanations

    text from research papers concerning data and phylogenetic tree alignment

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms

    np_token-act-pair-logits · gpt-4o-mini

    bioinformatics and genetics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     disambiguazione
    -0.56
     groom
    -0.50
     Roskov
    -0.49
    Hauptartikel
    -0.49
    клопе
    -0.47
    ferrer
    -0.47
    ogaster
    -0.46
    ixote
    -0.46
    crackers
    -0.45
     CHtml
    -0.45
    POSITIVE LOGITS
    InjectAttribute
    0.60
    PDOException
    0.57
    PreExecute
    0.52
    coroutines
    0.51
     kans
    0.50
    OrNil
    0.50
    Xna
    0.50
    cod
    0.50
    astify
    0.50
    Lähteet
    0.49
    Activations Density 2.437%

    No Known Activations