© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12769
    Prev
    Next
    INDEX
    Explanations

    phrases that relate to ensuring something

    oai_token-act-pair · gemini-2.0-flash

    ensure

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    addPreferredGap
    -0.85
    ThroughAttribute
    -0.83
    Personensuche
    -0.81
     nahilalakip
    -0.81
    QMetaType
    -0.79
    RenderAtEndOf
    -0.79
    DoubleQuotes
    -0.79
    RegressionTest
    -0.75
    tagHelperRunner
    -0.73
    новниш
    -0.71
    POSITIVE LOGITS
     a
    0.72
     high
    0.70
     that
    0.66
     the
    0.54
     an
    0.54
     micro
    0.52
    elsif
    0.50
     media
    0.50
     greater
    0.50
     full
    0.49
    Activations Density 4.067%

    No Known Activations