© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13592
    Prev
    Next
    INDEX
    Explanations

    units of measure, dates or political terms

    oai_token-act-pair · gemini-2.0-flash

    dates and measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ChildScrollView
    -0.51
     ***!
    -0.50
     محفوظة
    -0.49
     defStyle
    -0.49
    دانشنامهٔ
    -0.48
    QUADS
    -0.47
    DispatchToProps
    -0.47
     maille
    -0.46
    ChromeDriver
    -0.46
    klärt
    -0.46
    POSITIVE LOGITS
     للاسماء
    0.68
     endblock
    0.63
    StructEnd
    0.63
     <<<<<<<<<<<<<<
    0.60
     שוליים
    0.57
     ويكيميديا
    0.54
    Véxase
    0.53
    ylated
    0.53
     архивлан
    0.51
    ylation
    0.51
    Activations Density 8.471%

    No Known Activations