© 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. 12536
    Prev
    Next
    INDEX
    Explanations

    code, identifiers, and names used in computer software

    oai_token-act-pair · gemini-2.0-flash

    code/scientific text

    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
    ISupport
    -0.69
    HomeAsUpEnabled
    -0.66
    DotNetBar
    -0.66
    MergeFrom
    -0.65
    runApp
    -0.65
     continúas
    -0.64
    MarshalTo
    -0.63
    Affirmed
    -0.63
     chré
    -0.62
     sepen
    -0.62
    POSITIVE LOGITS
     MET
    0.60
    met
    0.54
    MENT
    0.54
     Met
    0.50
    ment
    0.50
    Datuak
    0.49
     Mem
    0.49
    MET
    0.49
    mets
    0.49
    menta
    0.48
    Activations Density 0.217%

    No Known Activations