© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7272
    Prev
    Next
    INDEX
    Explanations

    LaTeX math symbols

    oai_token-act-pair · gemini-2.0-flash

    math equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     cref
    -0.65
    >]
    -0.62
    ürger
    -0.56
    >"+
    -0.47
    >";
    -0.47
    "]/
    -0.47
    >")
    -0.46
     aspetto
    -0.45
    >`
    -0.45
    >';
    -0.43
    POSITIVE LOGITS
    WebElementEntity
    1.10
    leqq
    0.84
    WindowConstants
    0.73
    hdashline
    0.71
    SourceChecksum
    0.69
    sqcup
    0.68
    OrBuilder
    0.68
    TypedDataSet
    0.66
    lesssim
    0.66
     zuk
    0.62
    Activations Density 3.525%

    No Known Activations