© 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. 359
    Prev
    Next
    INDEX
    Explanations

    text that describes history, locations, and settlements

    oai_token-act-pair · gemini-2.0-flash

    Historical places and dates

    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
     Inscrivez
    -0.66
     senere
    -0.65
     senare
    -0.59
     You
    -0.56
     Puedes
    -0.55
     Você
    -0.55
     Connectez
    -0.55
    You
    -0.51
     Usted
    -0.49
     Theſe
    -0.47
    POSITIVE LOGITS
     AssemblyTitle
    0.71
     Reign
    0.70
    WriteLiteral
    0.70
    édrale
    0.69
    fromnode
    0.68
    MeasureSpec
    0.64
     Enix
    0.63
    ularia
    0.63
     propOrder
    0.62
    DotNetBar
    0.61
    Activations Density 7.518%

    No Known Activations