© 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. 1740
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a source or relationship

    oai_token-act-pair · gemini-2.0-flash

    quantities

    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
     يتيمه
    -0.52
    uxxxx
    -0.50
    ücks
    -0.48
    pédie
    -0.47
    urgery
    -0.45
    thello
    -0.43
    urtstag
    -0.43
     ControllerBase
    -0.42
    mogat
    -0.42
    unggulan
    -0.42
    POSITIVE LOGITS
     rates
    0.98
     prices
    0.93
     numbers
    0.88
     amounts
    0.82
     amount
    0.81
     levels
    0.77
     popularity
    0.75
     temperatures
    0.75
     quantity
    0.73
     incidence
    0.73
    Activations Density 2.671%

    No Known Activations