© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10758
    Prev
    Next
    INDEX
    Explanations

    acronyms, especially those related to three-dimensional imaging, computer-aided design, and medical imaging.

    oai_token-act-pair · gemini-2.0-flash

    D

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    =?";
    -0.53
    HideFlags
    -0.51
     AdapterView
    -0.51
     Chwiliwch
    -0.49
     shout
    -0.47
    awarkan
    -0.46
    olves
    -0.46
     still
    -0.46
    nieren
    -0.46
     出版
    -0.45
    POSITIVE LOGITS
    évaluateur
    0.75
    :✨
    0.73
    webElementXpaths
    0.72
    WebElementEntity
    0.71
    rungsseite
    0.69
     ComVisible
    0.66
     كومونز
    0.65
     يتيمه
    0.65
     مشين
    0.65
    
    0.63
    Activations Density 1.314%

    No Known Activations