© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1914
    Prev
    Next
    INDEX
    Explanations

    places where strings are concatenated in code, especially associated with error messages based on partial and uninformative code snippets

    oai_token-act-pair · gemini-2.0-flash

    Plus/addition

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    setVerticalGroup
    -0.78
    DataAnnotations
    -0.74
    featureID
    -0.71
    SourceChecksum
    -0.70
    webElementXpaths
    -0.69
    NameInMap
    -0.68
    -/**
    -0.67
     betweenstory
    -0.67
    endphp
    -0.66
     contextLoads
    -0.66
    POSITIVE LOGITS
    +
    1.36
    plus
    1.29
     Plus
    1.22
     plus
    1.16
    Plus
    1.14
    PLUS
    1.07
     PLUS
    1.00
    +.
    0.99
    +,
    0.92
    +)
    0.91
    Activations Density 6.134%

    No Known Activations