© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5891
    Prev
    Next
    INDEX
    Explanations

    dates and sports related terms

    oai_token-act-pair · gemini-2.0-flash

    Time periods, seasons

    np_max-act-logits · gemini-2.0-flash

    the

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    Portale
    -0.75
     Controller
    -0.68
     Connection
    -0.66
     Object
    -0.66
    Convey
    -0.65
     Connectors
    -0.65
     intptr
    -0.63
    Referanser
    -0.62
     Device
    -0.62
     Associ
    -0.62
    POSITIVE LOGITS
     Year
    0.84
     Season
    0.76
    Year
    0.73
     Summer
    0.67
     Week
    0.64
     Level
    0.63
     Decade
    0.62
    Season
    0.62
     Août
    0.59
     Temporada
    0.59
    Activations Density 13.993%

    No Known Activations