© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8963
    Prev
    Next
    INDEX
    Explanations

    dates, times, numbers, and brand names, often in a bulleted context, especially related to retail/shopping information

    oai_token-act-pair · gemini-2.0-flash

    numbers and dates

    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
    Kesimpulan
    -0.52
     typology
    -0.51
    Nomenclature
    -0.50
     authorship
    -0.49
     Shakspeare
    -0.49
     Pergamon
    -0.48
     nomenclature
    -0.47
     stratigraphy
    -0.47
    IMPLEMENTATION
    -0.46
     codif
    -0.45
    POSITIVE LOGITS
     يتيمه
    0.64
    bush
    0.54
    ագրություններ
    0.51
     Rose
    0.50
    JAM
    0.50
    MLB
    0.49
    fry
    0.49
    FRI
    0.49
     Hunt
    0.49
    Jackie
    0.48
    Activations Density 25.932%

    No Known Activations