© 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. 16244
    Prev
    Next
    INDEX
    Explanations

    words that have a high probability of appearing in a sentence

    oai_token-act-pair · gemini-2.0-flash

    general statements/opinions

    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
     BoxDecoration
    -0.63
     StatelessWidget
    -0.63
    ↵↵
    -0.58
    tymologie
    -0.58
     useStyles
    -0.57
     INTERESAR
    -0.55
     StatefulWidget
    -0.55
    sizeCache
    -0.53
     
    -0.51
     initComponents
    -0.51
    POSITIVE LOGITS
    <bos>
    0.80
    Grüße
    0.73
    ?
    0.69
    thâu
    0.69
    %</
    0.68
     cuantos
    0.67
     betweenstory
    0.67
    lecht
    0.67
     otomatig
    0.65
    Accomplished
    0.64
    Activations Density 6.934%

    No Known Activations