© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5518
    Prev
    Next
    INDEX
    Explanations

    the word "dog" or the word "spots"

    oai_token-act-pair · gemini-2.0-flash

    dog

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    Rüyada
    -0.52
    disposing
    -0.50
    IVEREF
    -0.50
    regi
    -0.49
    kell
    -0.49
    ervi
    -0.49
     Decorating
    -0.48
    úgó
    -0.47
    icksburg
    -0.46
     baja
    -0.46
    POSITIVE LOGITS
    تفصیلات
    0.88
    PerformLayout
    0.85
     تانيه
    0.69
     megt
    0.68
    válasz
    0.67
     mellett
    0.66
    الدراسه
    0.66
     архивлан
    0.65
    orghini
    0.64
    íté
    0.64
    Activations Density 0.177%

    No Known Activations