© 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. 16209
    Prev
    Next
    INDEX
    Explanations

    the word "stir", the words "compensation", "blur" and other words followed by a dollar sign "$" or concerned with financial calculations

    oai_token-act-pair · 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
    GraphicsUnit
    -0.98
    expandindo
    -0.93
     MenuView
    -0.88
     يتيمه
    -0.87
     '\\;'
    -0.86
    StreetMap
    -0.86
     Drapeau
    -0.81
     Италијани
    -0.79
    WillAppear
    -0.78
     Савезне
    -0.77
    POSITIVE LOGITS
     Diſ
    0.74
     bianchi
    0.72
     enfans
    0.69
     Perſ
    0.66
     reaſon
    0.64
     maroca
    0.62
     Reſ
    0.60
     quæ
    0.60
     peruan
    0.59
     ſtate
    0.59
    Activations Density 1.053%

    No Known Activations