© 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. 5283
    Prev
    Next
    INDEX
    Explanations

    the German word "aus" and the English word "stage"

    oai_token-act-pair · gemini-2.0-flash

    aus

    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
     long
    -0.69
    long
    -0.69
     longterm
    -0.50
    ciating
    -0.48
    ting
    -0.45
    inthe
    -0.44
    down
    -0.44
    fter
    -0.44
     serían
    -0.44
     Long
    -0.43
    POSITIVE LOGITS
     ModelExpression
    0.96
    <bos>
    0.93
    例句
    0.82
    :✨
    0.81
     wikipagina
    0.79
    omitempty
    0.78
    SharedCtor
    0.78
     GenerationType
    0.78
     autorytatywna
    0.77
    omock
    0.77
    Activations Density 3.012%

    No Known Activations