© 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. 1144
    Prev
    Next
    INDEX
    Explanations

    various kinds of punctuation and symbols that appear in code

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    lained
    -0.57
    POLE
    -0.54
     NoSuch
    -0.52
    stepping
    -0.50
     utafitiHapana
    -0.50
     cout
    -0.49
     kolei
    -0.49
    sou
    -0.48
    colle
    -0.48
    ншни
    -0.47
    POSITIVE LOGITS
    <bos>
    1.25
    TargetException
    0.72
     يتيمه
    0.71
    ParallelGroup
    0.66
     AssemblyCompany
    0.62
    ​—
    0.62
    _));
    0.60
    !")
    0.59
    |;
    0.59
    Становништво
    0.58
    Activations Density 2.671%

    No Known Activations