© 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. 6009
    Prev
    Next
    INDEX
    Explanations

    sentences describing how something is getting attention

    oai_token-act-pair · gemini-2.0-flash

    focus/attention

    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
    VIAF
    -0.76
    @[+][
    -0.75
    PreferredItem
    -0.73
    CloseOperation
    -0.73
    SharedDtor
    -0.69
     ExecuteAsync
    -0.69
     مشين
    -0.69
    DebuggerNonUser
    -0.67
    rawDesc
    -0.66
     initComponents
    -0.65
    POSITIVE LOGITS
     focus
    1.27
     spotlight
    1.17
     center
    1.16
     centre
    1.12
     front
    1.09
    focus
    1.05
    spotlight
    1.02
     Vordergrund
    0.96
    Focus
    0.96
    center
    0.96
    Activations Density 0.986%

    No Known Activations