© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14923
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to conclusions or the future

    oai_token-act-pair · gemini-2.0-flash

    end

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ViewImports
    -0.55
    )|^{
    -0.55
    pani
    -0.53
    LLocation
    -0.52
     réelle
    -0.49
    ticamente
    -0.49
    SYSC
    -0.49
    GLFW
    -0.48
    ėmis
    -0.48
     éc
    -0.48
    POSITIVE LOGITS
     of
    0.70
    Демографія
    0.50
    (!__
    0.49
    TargetException
    0.47
     الحره
    0.47
    partie
    0.46
    estias
    0.46
     tématu
    0.45
    \{\\
    0.45
     ◄
    0.45
    Activations Density 22.782%

    No Known Activations