© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12192
    Prev
    Next
    INDEX
    Explanations

    descriptive words and phrases with a sentimental undertone, perhaps related to choices and consequences

    oai_token-act-pair · gemini-2.0-flash

    course

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    endphp
    -0.54
    wamy
    -0.52
    ("}");
    -0.50
    enderror
    -0.49
    fikasi
    -0.47
     snippetHide
    -0.47
    lasma
    -0.46
    ViewById
    -0.46
    المكان
    -0.46
    GenerationType
    -0.45
    POSITIVE LOGITS
     course
    3.39
    course
    2.78
     Course
    2.73
     COURSE
    2.58
    Course
    2.58
     courses
    2.48
    COURSE
    2.17
     Courses
    2.14
     curso
    1.99
    courses
    1.95
    Activations Density 3.109%

    No Known Activations