© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11619
    Prev
    Next
    INDEX
    Explanations

    references to NFL American football games and seasons, particularly the scheduled dates and times that games are played

    oai_token-act-pair · gemini-2.0-flash

    days of the week

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     disambiguazione
    -0.96
    +#+
    -0.96
     itſelf
    -0.84
     propOrder
    -0.83
    ########.
    -0.83
     estekak
    -0.82
     ―――――
    -0.82
     myſelf
    -0.81
     Jefus
    -0.81
    mybatisplus
    -0.77
    POSITIVE LOGITS
    <bos>
    0.69
     host
    0.48
    bil
    0.47
    дя
    0.47
     stands
    0.45
    ղ
    0.45
    mu
    0.44
     hosts
    0.44
    felde
    0.44
    بع
    0.43
    Activations Density 0.223%

    No Known Activations