© 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. 5495
    Prev
    Next
    INDEX
    Explanations

    Java or C# code keywords like `new`, `long`, `byte`, `boolean`, `double`, `string`, `HashMap`, and `Document`

    oai_token-act-pair · gemini-2.0-flash

    Programming datatypes

    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
     heartbeat
    -0.79
     heart
    -0.65
     pulse
    -0.61
    heart
    -0.61
     beating
    -0.60
    heartbeat
    -0.60
     fabric
    -0.58
    Heart
    -0.54
     of
    -0.52
     soul
    -0.51
    POSITIVE LOGITS
    saraba
    0.72
     виправивши
    0.71
     defaultstate
    0.70
    Hentet
    0.70
    GraphicsUnit
    0.69
     ]
    0.68
    NUMX
    0.68
    ")){
    0.68
     الحره
    0.66
    $.
    0.66
    Activations Density 0.948%

    No Known Activations