© 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. 3586
    Prev
    Next
    INDEX
    Explanations

    words and names associated with baseball

    oai_token-act-pair · 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
    vician
    -0.77
    aarrggbb
    -0.76
    AddTagHelper
    -0.71
     initComponents
    -0.69
    InjectAttribute
    -0.65
    DeleteBehavior
    -0.65
    SharedCtor
    -0.64
    Билгалдахарш
    -0.64
     CreateTagHelper
    -0.64
    MemoryWarning
    -0.63
    POSITIVE LOGITS
    toPromise
    0.50
     ferroviaire
    0.49
    ulco
    0.46
    ayam
    0.44
     olympique
    0.43
    kaufs
    0.42
    lorus
    0.42
     Forms
    0.42
    EndContext
    0.41
    MockMvc
    0.41
    Activations Density 4.665%

    No Known Activations