© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13300
    Prev
    Next
    INDEX
    Explanations

    tokens frequently used in academic papers about math and other scientific topics

    oai_token-act-pair · gemini-2.0-flash

    multi

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     noDo
    -0.66
    tagHelper
    -0.60
    +:+
    -0.56
    sizeCache
    -0.55
    insegna
    -0.53
     ModelExpression
    -0.52
    __':
    -0.52
    AutoScale
    -0.50
    queda
    -0.49
     altrett
    -0.49
    POSITIVE LOGITS
    AsStream
    0.63
    port
    0.51
    XmlType
    0.50
    Vidite
    0.49
     droog
    0.48
     Domini
    0.47
     Beckett
    0.47
    وصلات
    0.47
     Chromatography
    0.46
    uchi
    0.46
    Activations Density 7.512%

    No Known Activations