© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9812
    Prev
    Next
    INDEX
    Explanations

    phrases with positive sentiment about work that somebody is doing, including helping others

    oai_token-act-pair · gemini-2.0-flash

    job

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     mergeFrom
    -0.59
    mapStateToProps
    -0.59
     segre
    -0.57
    APORE
    -0.55
    contentLoaded
    -0.54
     marat
    -0.49
    urahan
    -0.49
    ilitation
    -0.49
     allAfrica
    -0.47
    גה
    -0.46
    POSITIVE LOGITS
    ReusableCell
    0.78
    AnchorTagHelper
    0.63
    baguna
    0.57
    DoubleQuotes
    0.57
    WGS
    0.54
    DeleteBehavior
    0.54
    RenderAtEndOf
    0.54
    Cursors
    0.54
    CppCodeGen
    0.53
    Flammability
    0.52
    Activations Density 2.665%

    No Known Activations