© 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. 10934
    Prev
    Next
    INDEX
    Explanations

    words involved in DNA processing, file modification, or programming tasks

    oai_token-act-pair · gemini-2.0-flash

    shearing

    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
    KommentareTeilen
    -0.79
    новништво
    -0.72
    CppMethod
    -0.66
    RegressionTest
    -0.65
     tslint
    -0.64
     xenia
    -0.64
    +:+
    -0.63
     iprot
    -0.62
    цездатний
    -0.61
    JspWriter
    -0.60
    POSITIVE LOGITS
    HtmlAttribute
    0.51
    shadowRadius
    0.45
     insuffisamment
    0.44
     significant
    0.42
    cassert
    0.42
    cdnjs
    0.41
    withIdentifier
    0.40
    getTag
    0.40
    Tag
    0.40
     /\.(
    0.40
    Activations Density 2.612%

    No Known Activations