© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11706
    Prev
    Next
    INDEX
    Explanations

    astrophysics journal references

    oai_token-act-pair · gemini-2.0-flash

    technical terms and code-related keywords

    np_token-act-pair-logits · gpt-4o-mini

    Scientific citations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    VIAF
    -0.48
     vaih
    -0.46
    XmlAccessType
    -0.44
     Spart
    -0.43
     שוליים
    -0.43
    source
    -0.42
     widow
    -0.41
    UGS
    -0.40
    ーター
    -0.40
     crutches
    -0.40
    POSITIVE LOGITS
    ChildScrollView
    0.77
    rungsseite
    0.64
    FXMLLoader
    0.61
     المعيارى
    0.61
    CppMethod
    0.60
     متعلقه
    0.59
     onData
    0.59
     تضيفلها
    0.58
     AssemblyProduct
    0.57
    coden
    0.57
    Activations Density 0.480%

    No Known Activations