© 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. 5336
    Prev
    Next
    INDEX
    Explanations

    words or short phrases related to algorithms, feature selection, and data analysis

    oai_token-act-pair · gemini-2.0-flash

    prioritization and ranking

    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
    SourceChecksum
    -0.80
     المعيارى
    -0.67
     surla
    -0.61
     Baillargeon
    -0.56
     estekak
    -0.56
    toggler
    -0.54
     resourceCulture
    -0.54
    epik
    -0.54
     Numerade
    -0.52
    ConstraintMaker
    -0.52
    POSITIVE LOGITS
     priority
    1.02
     prioriti
    1.01
     prioritize
    0.98
     prioritized
    0.97
     weights
    0.97
     ranked
    0.94
     ranking
    0.94
     priorities
    0.93
    weight
    0.90
     prioritise
    0.90
    Activations Density 5.547%

    No Known Activations