© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3152
    Prev
    Next
    INDEX
    Explanations

    words relating to the kotlin Dokka documentation engine and film festivals

    oai_token-act-pair · gemini-2.0-flash

    umen/ary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    jsonwebtoken
    -0.83
    脚注の使い方
    -0.79
    الإنجليزية
    -0.78
    AccessorTable
    -0.75
    VersionUID
    -0.71
    帖最后由
    -0.69
     AssemblyVersion
    -0.67
     Мексичка
    -0.67
    ScopeManager
    -0.66
    بوابة
    -0.66
    POSITIVE LOGITS
     document
    0.52
    ColumnHeaders
    0.51
     documents
    0.51
    ValueStyle
    0.49
    ьажоргаш
    0.48
    Nonsense
    0.48
    ervos
    0.48
    izziness
    0.47
     finos
    0.46
    eabouts
    0.45
    Activations Density 0.393%

    No Known Activations