© 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. 14725
    Prev
    Next
    INDEX
    Explanations

    words used in programming and software documentation, especially Portuguese words related to programming

    oai_token-act-pair · gemini-2.0-flash

    Code and debugging

    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
     تضيفلها
    -0.65
     themſelves
    -0.58
    ließlich
    -0.52
     którzy
    -0.52
     Jefus
    -0.50
    ijuana
    -0.49
    Eksterne
    -0.49
    astéroïdes
    -0.49
    Descripció
    -0.49
    coeffs
    -0.48
    POSITIVE LOGITS
    Datuak
    0.66
    /******/
    0.57
    Portail
    0.56
    cèse
    0.54
    ГЛА
    0.54
    #
    0.52
    tagHelperRunner
    0.51
    getahuan
    0.49
    migrationBuilder
    0.48
    :✨
    0.48
    Activations Density 1.258%

    No Known Activations