© 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. 8501
    Prev
    Next
    INDEX
    Explanations

    words in the computer and games/sports/building/writing context

    oai_token-act-pair · gemini-2.0-flash

    birth/marriage

    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
     purpoſe
    -0.57
     contextLoads
    -0.57
     ")");
    -0.56
     myſelf
    -0.55
    Források
    -0.53
     stie
    -0.50
    fay
    -0.50
     itſelf
    -0.49
    DotNetBar
    -0.49
     coven
    -0.49
    POSITIVE LOGITS
     birth
    0.81
     married
    0.81
     baby
    0.75
     alive
    0.72
     marriage
    0.71
    married
    0.69
    BIRTH
    0.69
    birth
    0.67
    marriage
    0.67
     BIRTH
    0.66
    Activations Density 2.685%

    No Known Activations