© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 750
    Prev
    Next
    INDEX
    Explanations

    geographical locations and sports teams

    oai_token-act-pair · gemini-2.0-flash

    sports clubs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Sport
    -0.76
     professional
    -0.75
     club
    -0.73
    Professional
    -0.73
     sport
    -0.73
    professional
    -0.73
     clubs
    -0.71
    Sports
    -0.71
    sport
    -0.71
    SPORTS
    -0.69
    POSITIVE LOGITS
    rrggbb
    0.62
     springfox
    0.54
    asto
    0.53
    gonic
    0.52
    TextWatcher
    0.51
     magasiner
    0.51
    SequentialGroup
    0.50
     /\.(
    0.50
    Fordítás
    0.50
    protoc
    0.49
    Activations Density 1.732%

    No Known Activations