© 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. 14119
    Prev
    Next
    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gemini-2.0-flash

    begin

    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
    writeField
    -0.50
    POSURE
    -0.49
    )"),
    -0.48
     venons
    -0.47
    tifkan
    -0.46
    ้ม
    -0.45
     Obrador
    -0.45
     zimowa
    -0.44
     Sheet
    -0.44
    wired
    -0.44
    POSITIVE LOGITS
     nakalista
    0.61
    matchCondition
    0.60
    createCanvas
    0.58
    GEBURTSDATUM
    0.58
    AsUp
    0.57
    Искәрмәләр
    0.55
    MockBean
    0.55
     חיצוניים
    0.54
    arnos
    0.54
    bürger
    0.53
    Activations Density 5.060%

    No Known Activations