© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10105
    Prev
    Next
    INDEX
    Explanations

    a mix of Russian, Serbian and German words related to doing something or getting something

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    ReusableCell
    -0.64
    RectangleBorder
    -0.64
    ScopeManager
    -0.61
    ImageContext
    -0.60
    mybatisplus
    -0.59
     BrowserModule
    -0.58
     مشين
    -0.57
    PreAuthorize
    -0.56
    writeHead
    -0.56
    estris
    -0.56
    POSITIVE LOGITS
    <bos>
    1.19
     кроме
    0.63
     Савезне
    0.62
     sufrido
    0.57
    出版年
    0.54
    eachtet
    0.52
     endregion
    0.51
    Jeografia
    0.51
    SharedCtor
    0.51
     كومونز
    0.50
    Activations Density 1.022%

    No Known Activations