© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2249
    Prev
    Next
    INDEX
    Explanations

    the word "assembly" in what appears to be a code file

    oai_token-act-pair · gemini-2.0-flash

    assembly

    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
     виправивши
    -1.01
    RegressionTest
    -0.86
    ViewImports
    -0.84
    DeleteBehavior
    -0.81
    protoimpl
    -0.73
     متعلقه
    -0.68
     protoimpl
    -0.68
    ArrowToggle
    -0.67
     ujednoznacz
    -0.66
    providedIn
    -0.64
    POSITIVE LOGITS
    URBANA
    0.53
    <bos>
    0.50
    kim
    0.49
    tispiece
    0.47
    putInt
    0.46
    foreach
    0.46
    opardy
    0.44
     inspiring
    0.44
    tim
    0.44
    am
    0.43
    Activations Density 0.030%

    No Known Activations