© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7348
    Prev
    Next
    INDEX
    Explanations

    the act of predicting something impossible to know for the short and long term

    oai_token-act-pair · gemini-2.0-flash

    forecasting

    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
    ⓧ
    -0.75
     pinulongan
    -0.69
    XmlAccessorType
    -0.66
    SourceChecksum
    -0.65
    messageInfo
    -0.63
    complexContent
    -0.63
     nahilalakip
    -0.62
     ComVisible
    -0.62
    ">—
    -0.61
    UnknownFieldSet
    -0.60
    POSITIVE LOGITS
     forecast
    1.27
     prediction
    1.11
     forecasts
    1.09
     forecasting
    1.09
     Forecast
    1.07
     predict
    1.02
     predictions
    1.02
    forecast
    1.00
     FORECAST
    0.99
    Forecast
    0.98
    Activations Density 1.237%

    No Known Activations