© 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. 984
    Prev
    Next
    INDEX
    Explanations

    a variety of words related to academics, locations, scientific terms, Indian food, and other random terms.

    oai_token-act-pair · gemini-2.0-flash

    Technical documents

    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
    +#+#
    -0.47
    <u>
    -0.44
    SPATH
    -0.43
     Pernambuco
    -0.42
     Gouverneur
    -0.42
    SqlClient
    -0.42
     stabilization
    -0.41
    ג
    -0.40
    <strong>
    -0.40
    де
    -0.40
    POSITIVE LOGITS
    webElementXpaths
    0.78
     Мексичка
    0.71
    <bos>
    0.67
    Bakgrunnsstoff
    0.59
     isInitialized
    0.59
    MLLoader
    0.58
    Tujuan
    0.57
    Màu
    0.57
     EnglishChoose
    0.56
    RTLD
    0.56
    Activations Density 4.265%

    No Known Activations