© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12902
    Prev
    Next
    INDEX
    Explanations

    words related to records, medicine, war, DNA, databases, leaders, and the military

    oai_token-act-pair · gemini-2.0-flash

    official documents/personnel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    setVerticalGroup
    -0.82
    MemoryWarning
    -0.79
    abestanden
    -0.72
    igshid
    -0.71
    ServletException
    -0.70
    UnitTesting
    -0.70
    SpringRunner
    -0.68
    !*\
    -0.66
     ویکی‌پدیا
    -0.66
    Diwedd
    -0.66
    POSITIVE LOGITS
    <bos>
    0.85
    InsertCommand
    0.49
     Roskov
    0.47
    oneofs
    0.46
    einander
    0.46
    seitige
    0.45
     mans
    0.45
     rentrée
    0.44
    karena
    0.43
    are
    0.43
    Activations Density 1.739%

    No Known Activations