Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1586
    Prev
    Next
    INDEX
    Explanations

    monetary values in the format of a dollar sign followed by a number

    oai_token-act-pair · gemini-2.0-flash

    Code and tables

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    &
    -1.71
    \&
    -1.30
    .&
    -1.09
    )&
    -0.95
    }&
    -0.77
    ,&
    -0.75
    ]&
    -0.73
    ;&
    -0.73
    &(
    -0.70
    !&
    -0.69
    POSITIVE LOGITS
    Personendaten
    0.82
     للمعارف
    0.75
    WithIOException
    0.71
    principalColumn
    0.70
     Paglinawan
    0.67
     intptr
    0.66
    onAttach
    0.65
    IsContent
    0.65
    ViewFeatures
    0.62
     صوتيه
    0.62
    Activations Density 3.389%

    No Known Activations