© 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. 9959
    Prev
    Next
    INDEX
    Explanations

    the keyword "as" in code. That likely implies that it is finding alias assignments

    oai_token-act-pair · gemini-2.0-flash

    as

    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
    NameInMap
    -0.65
    Identyfik
    -0.59
     getModel
    -0.57
     ProtoMessage
    -0.50
    inctions
    -0.49
     OFDb
    -0.49
    IndentedString
    -0.47
    eaker
    -0.46
     pourtant
    -0.45
     Pauly
    -0.45
    POSITIVE LOGITS
    <bos>
    1.07
    #
    0.85
    /*
    0.65
     whiteColor
    0.56
    MemoryWarning
    0.54
    tissement
    0.54
    úgó
    0.54
     chiam
    0.52
     visit
    0.51
    olución
    0.50
    Activations Density 0.301%

    No Known Activations