© 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. 9852
    Prev
    Next
    INDEX
    Explanations

    sports related articles with team names, stats and scores, especially related to football and basketball

    oai_token-act-pair · gemini-2.0-flash

    sports seasons

    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
    InjectAttribute
    -0.77
    PropertyGroup
    -0.74
    SourceChecksum
    -0.72
     يتيمه
    -0.71
    Sucesor
    -0.71
    ########.
    -0.68
     esternos
    -0.66
     AssemblyTitle
    -0.65
    XmlType
    -0.63
    principalTable
    -0.62
    POSITIVE LOGITS
     Pacers
    0.49
     Anſ
    0.47
     Hornets
    0.45
    ARIUS
    0.45
     itſelf
    0.44
    nons
    0.43
     Vikings
    0.41
     Falls
    0.41
    zers
    0.40
     DPS
    0.40
    Activations Density 7.935%

    No Known Activations