© 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. 3768
    Prev
    Next
    INDEX
    Explanations

    words related to academic research papers describing new methods

    oai_token-act-pair · gemini-2.0-flash

    method

    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>
    -1.91
    RenderAtEndOf
    -0.84
     للمعارف
    -0.76
     Paglinawan
    -0.74
    tagHelperRunner
    -0.69
    Демографія
    -0.69
     समीक्षाओं
    -0.66
     typelib
    -0.66
    setVerticalGroup
    -0.64
     للاسماء
    -0.64
    POSITIVE LOGITS
    icae
    0.61
    logi
    0.57
    QUENCE
    0.54
    braucher
    0.54
     seres
    0.53
    arot
    0.52
    medios
    0.51
    IMON
    0.50
    arel
    0.50
     Otero
    0.49
    Activations Density 21.611%

    No Known Activations