© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10535
    Prev
    Next
    INDEX
    Explanations

    discusses trends, statistics, and recent popular culture

    oai_token-act-pair · gemini-2.0-flash

    trends

    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
     trend
    -2.77
     Trend
    -2.58
     trends
    -2.56
    Trend
    -2.53
    trend
    -2.44
     Trends
    -2.31
    Trends
    -2.31
    trends
    -2.17
     trending
    -2.13
     TRENDS
    -2.05
    POSITIVE LOGITS
    PMailer
    0.72
     pinulongan
    0.66
    ỡng
    0.64
    StructEnd
    0.64
    portlet
    0.63
     ffilm
    0.63
     للمعارف
    0.62
     تانيه
    0.61
    istoitu
    0.61
    devamını
    0.60
    Activations Density 1.590%

    No Known Activations