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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10909
    Prev
    Next
    INDEX
    Explanations

    mentions of courses, especially when combined with terms like "materials" or "costs"

    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
     course
    -1.00
     Course
    -0.95
     COURSE
    -0.94
    ValueStyle
    -0.92
    Course
    -0.86
    course
    -0.79
    COURSE
    -0.79
    SharedCtor
    -0.75
     courses
    -0.73
    RTDA
    -0.73
    POSITIVE LOGITS
    REQUIRES
    0.46
    !*\
    0.45
    arvi
    0.44
     Arrondissement
    0.43
    em
    0.43
    mentaires
    0.42
     Verpackung
    0.42
     الحره
    0.40
    ('',
    0.40
     дизайна
    0.40
    Activations Density 4.145%

    No Known Activations