© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6380
    Prev
    Next
    INDEX
    Explanations

    the word "maintained"

    oai_token-act-pair · gemini-2.0-flash

    maintained

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     maintain
    -2.30
     maintained
    -2.28
     maintenance
    -2.27
    maintain
    -2.17
     maintaining
    -2.14
     Maintaining
    -2.13
     Maintenance
    -2.13
     Maintain
    -2.11
     maintains
    -2.09
    Maintaining
    -2.06
    POSITIVE LOGITS
    ArgsConstructor
    0.90
     AssemblyProduct
    0.79
    
    0.77
     مشين
    0.76
     insuffisamment
    0.67
     NSCoder
    0.65
    RectangleBorder
    0.61
     متعلقه
    0.60
    gsSP
    0.59
    각주
    0.57
    Activations Density 0.995%

    No Known Activations