© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16027
    Prev
    Next
    INDEX
    Explanations

    computer commands/API calls

    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
    ”,
    -1.19
     “,
    -1.05
    “,
    -1.05
    ’,
    -1.05
     ",
    -1.02
    ”.
    -0.91
    ",
    -0.90
    ,”
    -0.90
     ',
    -0.88
    `,
    -0.86
    POSITIVE LOGITS
    <bos>
    0.85
     Wikimedijinoj
    0.64
    ()?;
    0.63
    */),
    0.61
    RunWith
    0.60
     GeoNames
    0.59
    UrlResolution
    0.59
    WHEREAS
    0.59
    NameInMap
    0.59
    XmlAccessType
    0.59
    Activations Density 0.480%

    No Known Activations