© 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. 4335
    Prev
    Next
    INDEX
    Explanations

    dates as well as people involved in creating memorials, inventions, or works of art

    oai_token-act-pair · gemini-2.0-flash

    inventions and historical figures

    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
    Doctor
    -0.66
     Doctor
    -0.65
     DOCTOR
    -0.60
     dr
    -0.57
    DOCTOR
    -0.56
     doctor
    -0.54
     Dr
    -0.53
    #
    -0.52
     pro
    -0.52
    Dr
    -0.51
    POSITIVE LOGITS
     насељу
    0.95
    endphp
    0.91
    parsedMessage
    0.87
     onCancelled
    0.82
    oredCriteria
    0.81
    TypedDataSet
    0.77
    ValueGeneration
    0.77
    ThroughAttribute
    0.75
    BufferException
    0.73
    цездатний
    0.72
    Activations Density 0.615%

    No Known Activations