© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6626
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and the surrounding explanation

    oai_token-act-pair · gemini-2.0-flash

    algorithms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    SerializedSize
    -0.64
     JAXBElement
    -0.60
     msglen
    -0.59
     Lessing
    -0.56
     hàm
    -0.56
    hmigung
    -0.55
    PCell
    -0.54
     hébergement
    -0.54
    Jawaban
    -0.54
    Хьажоргаш
    -0.53
    POSITIVE LOGITS
    onViewCreated
    0.53
    Mounted
    0.52
     Cove
    0.46
    globalData
    0.45
    */)
    0.45
     spot
    0.44
     հղումներ
    0.43
    ContentAsync
    0.42
    JspWriter
    0.42
    Mp
    0.41
    Activations Density 5.098%

    No Known Activations