© 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. 2721
    Prev
    Next
    INDEX
    Explanations

    words and phrases used in scientific papers

    oai_token-act-pair · gemini-2.0-flash

    and

    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
    <bos>
    -1.67
    rungsseite
    -0.79
     estekak
    -0.77
     كومونز
    -0.70
    /*
    -0.69
    __':
    -0.65
     Савезне
    -0.63
     <=",
    -0.63
     endregion
    -0.62
    UnusedPrivate
    -0.62
    POSITIVE LOGITS
    ContextCompat
    0.56
     sarili
    0.55
    amom
    0.54
    ried
    0.53
     bulk
    0.52
    водство
    0.52
    oneer
    0.50
    GHIJKLM
    0.50
    minist
    0.50
     preparation
    0.49
    Activations Density 6.369%

    No Known Activations