© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13922
    Prev
    Next
    INDEX
    Explanations

    words and numbers relating to sports statistics, including football but also other sports

    oai_token-act-pair · gemini-2.0-flash

    Sports events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     leçon
    -0.53
    '){
    -0.52
     game
    -0.52
    ()]);
    -0.51
    ("")]
    -0.48
    icamente
    -0.48
    ")){
    -0.47
    IUrlHelper
    -0.47
    لينكات
    -0.47
     مشين
    -0.47
    POSITIVE LOGITS
    URBANA
    0.67
     Vikipedi
    0.66
    #+#
    0.65
     games
    0.65
     races
    0.65
    sproz
    0.63
    XmlAccessType
    0.62
    出版年
    0.59
     Races
    0.58
     matchups
    0.58
    Activations Density 8.222%

    No Known Activations