© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11225
    Prev
    Next
    INDEX
    Explanations

    information from sports games, particularly scores, names of teams, and game-related jargon

    oai_token-act-pair · gemini-2.0-flash

    Sports reporting

    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
    Datuak
    -0.64
     dAtA
    -0.53
    djangoproject
    -0.52
     >=",
    -0.52
     Résultat
    -0.51
    adaptiveStyles
    -0.48
     dags
    -0.48
     AspNetCore
    -0.48
    isContained
    -0.48
    obod
    -0.47
    POSITIVE LOGITS
    ServiceTest
    0.56
     Kings
    0.53
     Normdatei
    0.51
    bildung
    0.49
    simum
    0.49
    indd
    0.48
    ayam
    0.48
    iense
    0.48
     Sachs
    0.48
    eadas
    0.48
    Activations Density 17.994%

    No Known Activations