© 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. 1806
    Prev
    Next
    INDEX
    Explanations

    words related to processes, progress and multiple examples of the same thing

    oai_token-act-pair · gemini-2.0-flash

    research/reports

    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
    Hozzáférés
    -0.50
    ссажи
    -0.46
    Begriffsklä
    -0.45
    XmlAccessorType
    -0.43
    pacs
    -0.41
    taj
    -0.40
     er
    -0.39
    """
    -0.39
     apparent
    -0.38
     которое
    -0.38
    POSITIVE LOGITS
    ImageContext
    0.79
     TextAppearance
    0.75
     Roskov
    0.72
    orianCalendar
    0.69
    +:+
    0.69
     مشين
    0.68
    kháu
    0.66
     للاسماء
    0.65
     ostavi
    0.65
    ukone
    0.64
    Activations Density 22.852%

    No Known Activations