© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4209
    Prev
    Next
    INDEX
    Explanations

    a mix of terms related to buildings and also the phrase "stakes are high."

    oai_token-act-pair · gemini-2.0-flash

    terms related to height

    np_token-act-pair-logits · gpt-4o-mini

    high

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    OGND
    -0.66
     AssemblyTitle
    -0.65
    webElementXpaths
    -0.52
     createState
    -0.50
     eventdata
    -0.48
    Hauptartikel
    -0.46
    AxisSize
    -0.46
    AlterField
    -0.46
    NTIS
    -0.45
    RefNanny
    -0.45
    POSITIVE LOGITS
     high
    1.77
    high
    1.52
     higher
    1.43
    High
    1.36
     High
    1.34
    高
    1.30
     HIGH
    1.30
     tinggi
    1.30
    HIGH
    1.29
     hight
    1.19
    Activations Density 1.938%

    No Known Activations