© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10783
    Prev
    Next
    INDEX
    Explanations

    scientific text involving parameters, equations, and statistical measures, possibly in the field of astrophysics or cosmology

    oai_token-act-pair · gemini-2.0-flash

    code-related terms and function names

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

    cosmological models

    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
     незавершена
    -0.77
    XmlAccessType
    -0.70
     propOrder
    -0.67
    StackNavigator
    -0.66
    acamata
    -0.65
     invokingState
    -0.63
    DotNetBar
    -0.63
    @[+][
    -0.62
     AssemblyProduct
    -0.61
    XmlAccessorType
    -0.60
    POSITIVE LOGITS
    WriteAttribute
    0.56
     pe
    0.51
     Wetter
    0.49
    Geografia
    0.48
     initComponents
    0.47
    makeConstraints
    0.41
    ChildScrollView
    0.41
    Afrika
    0.40
     pri
    0.40
     block
    0.40
    Activations Density 4.878%

    No Known Activations