© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5615
    Prev
    Next
    INDEX
    Explanations

    capitalized abbreviations, especially acronyms, initialisms and shortened forms of words, often technical or scientific.

    oai_token-act-pair · gemini-2.0-flash

    Abbreviations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    которые
    -1.04
    foundland
    -0.87
    нрави
    -0.85
    tonsoft
    -0.75
    ilever
    -0.73
    dawnictwo
    -0.73
    richlet
    -0.72
    oughby
    -0.70
    nyata
    -0.70
    envolvimento
    -0.69
    POSITIVE LOGITS
    guien
    0.70
    stood
    0.65
     AssemblyCompany
    0.63
     незавершена
    0.60
    ocidad
    0.56
    здрав
    0.56
    tualmente
    0.54
    OfWeek
    0.54
    cestor
    0.54
    ButtonModule
    0.52
    Activations Density 2.578%

    No Known Activations