© 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. 13808
    Prev
    Next
    INDEX
    Explanations

    numbers and dates, especially when relating to statistics or categorization

    oai_token-act-pair · gemini-2.0-flash

    technical / research text

    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
    <bos>
    -0.11
     varandra
    0.05
     Efq
    0.08
     quelcon
    0.09
     actuels
    0.09
     traditionnels
    0.10
     gånger
    0.10
     stället
    0.10
    ^(@)
    0.10
     regeringen
    0.10
    POSITIVE LOGITS
    MigrationBuilder
    0.65
    出版年
    0.61
     autorytatywna
    0.59
     تضيفلها
    0.58
    RenderAtEndOf
    0.57
     ویکی‌پدی
    0.57
    GEBURTSDATUM
    0.56
    Personensuche
    0.56
    reu
    0.55
    tagHelperRunner
    0.55
    Activations Density 13.400%

    No Known Activations