© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7254
    Prev
    Next
    INDEX
    Explanations

    descriptions of a football (soccer) team playing well

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     history
    -0.90
    history
    -0.88
     History
    -0.85
     HISTORY
    -0.84
    HISTORY
    -0.81
    History
    -0.78
     sejarah
    -0.76
     Roskov
    -0.75
     histories
    -0.75
     historia
    -0.66
    POSITIVE LOGITS
     initComponents
    0.54
     attacking
    0.54
     play
    0.54
    play
    0.53
     PrintWriter
    0.52
    CreateModel
    0.52
     finger
    0.51
     playing
    0.50
    playing
    0.50
     Ofrece
    0.50
    Activations Density 0.702%

    No Known Activations