© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2714
    Prev
    Next
    INDEX
    Explanations

    references to dates and history

    oai_token-act-pair · gemini-2.0-flash

    timing of events

    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
    NameInMap
    -0.82
    _));
    -0.65
    titleMargin
    -0.63
     &___
    -0.63
    DoubleQuotes
    -0.60
    évaluateur
    -0.55
    ViewFeatures
    -0.54
    StructEnd
    -0.54
    MessageTagHelper
    -0.54
    CppMethod
    -0.54
    POSITIVE LOGITS
     surviving
    0.81
     earliest
    0.72
     early
    0.70
    early
    0.68
     Early
    0.68
     sobrevi
    0.66
     stammt
    0.65
    Early
    0.65
     EARLY
    0.64
    late
    0.63
    Activations Density 2.611%

    No Known Activations