© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13945
    Prev
    Next
    INDEX
    Explanations

    discourse markers at the start of a sentence to introduce a topic or opinion shift

    oai_token-act-pair · gemini-2.0-flash

    So

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     and
    -0.39
    <bos>
    -0.38
    Citiți
    -0.36
     pymysql
    -0.36
     ElevatedButton
    -0.36
    Neben
    -0.34
     Happened
    -0.34
    )|^{
    -0.33
    formik
    -0.32
    stress
    -0.32
    POSITIVE LOGITS
     ModelExpression
    0.91
     AssemblyCulture
    0.85
    Hentet
    0.79
     <<<<<<<<<<<<<<
    0.73
     الرياضيه
    0.72
    NameInMap
    0.72
    ImageContext
    0.69
     nahilalakip
    0.68
    ists
    0.67
    critto
    0.66
    Activations Density 10.500%

    No Known Activations