© 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. 12938
    Prev
    Next
    INDEX
    Explanations

    the word "legacy"

    oai_token-act-pair · gemini-2.0-flash

    legacy

    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
    <bos>
    -0.97
     success
    -0.64
    /');
    -0.57
    ]');
    -0.54
    ]");
    -0.52
    '].
    -0.51
    ]";
    -0.51
    ")))
    -0.51
    '");
    -0.50
    "].
    -0.50
    POSITIVE LOGITS
     AssemblyCulture
    0.87
    ViewFeatures
    0.78
    :✨
    0.72
     Violation
    0.69
     TextAppearance
    0.67
    TagMode
    0.66
     JUSTICE
    0.65
    hythm
    0.65
    diat
    0.65
     Elders
    0.63
    Activations Density 0.644%

    No Known Activations