© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 11245
    Prev
    Next
    INDEX
    Explanations

    terms related to data analysis with a focus on machine learning and statistics

    oai_token-act-pair · gemini-2.0-flash

    machine learning algorithms

    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
    WebServlet
    -0.50
    
    -0.48
    PreInfinity
    -0.45
    opheles
    -0.45
    chn
    -0.44
     created
    -0.43
    OnAdd
    -0.43
    Creating
    -0.43
     @"/
    -0.43
     szeret
    -0.42
    POSITIVE LOGITS
    Hozzáférés
    0.76
     متعلقه
    0.55
    Diwedd
    0.54
    Życiorys
    0.51
    mAuth
    0.50
    Migrations
    0.50
    quiries
    0.50
     समीक्षाओं
    0.50
    aneously
    0.49
    InSection
    0.48
    Activations Density 3.396%

    No Known Activations