© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5991
    Prev
    Next
    INDEX
    Explanations

    what looks like program code

    oai_token-act-pair · gemini-2.0-flash

    Code/technical documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    oredCriteria
    -0.81
     تضيفلها
    -0.81
    WithIOException
    -0.77
    NewUrlParser
    -0.75
    DockStyle
    -0.75
    CloseOperation
    -0.75
    IntoConstraints
    -0.73
    AccessorTable
    -0.72
     Administrativna
    -0.71
     Wicidata
    -0.70
    POSITIVE LOGITS
    BagLayout
    0.51
    uras
    0.46
    sign
    0.44
    META
    0.42
    world
    0.41
     oport
    0.40
     sentiment
    0.39
    anie
    0.39
    unner
    0.39
    con
    0.38
    Activations Density 5.109%

    No Known Activations