© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11659
    Prev
    Next
    INDEX
    Explanations

    code snippets and related keywords such as "set", "distinct", "Boolean", and "assert".

    oai_token-act-pair · gemini-2.0-flash

    code using sets

    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
     array
    -0.69
     Array
    -0.65
    ArrayOf
    -0.60
     chứa
    -0.60
     containing
    -0.59
    ARRAY
    -0.58
     ArrayList
    -0.58
    NSMutableArray
    -0.57
    Array
    -0.56
     list
    -0.55
    POSITIVE LOGITS
    PhysRevLett
    0.70
    بوابة
    0.70
    StructEnd
    0.69
    FunctionFlags
    0.66
    DeleteBehavior
    0.65
    ftc
    0.60
     betweenstory
    0.60
    errHandler
    0.59
    piram
    0.59
    IComponent
    0.58
    Activations Density 3.223%

    No Known Activations