© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8570
    Prev
    Next
    INDEX
    Explanations

    years represented as four digit numbers

    oai_token-act-pair · gemini-2.0-flash

    predictions about future years

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Мексичка
    -0.81
     Efq
    -0.69
     Réponses
    -0.66
    CodeAttribute
    -0.64
     Puro
    -0.63
     Majefty
    -0.62
    DoubleQuotes
    -0.60
    nissen
    -0.59
    ThroughAttribute
    -0.59
    كتوبر
    -0.59
    POSITIVE LOGITS
     CURIAM
    0.64
     الحره
    0.55
    WaitGroup
    0.52
    tagHelperRunner
    0.46
    ше
    0.45
    ander
    0.45
    Tại
    0.44
    SequentialGroup
    0.44
    DispatchToProps
    0.43
    PCell
    0.42
    Activations Density 0.234%

    No Known Activations