© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3685
    Prev
    Next
    INDEX
    Explanations

    score ratings

    oai_token-act-pair · gemini-2.0-flash

    references to movie ratings or scores

    np_token-act-pair-logits · gpt-4o-mini

    ratings with numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Hozzáférés
    -0.52
    ContentAsync
    -0.51
     IntelliJ
    -0.50
     برابوك
    -0.49
    breath
    -0.49
     demek
    -0.47
    tawesome
    -0.47
    ParallelGroup
    -0.47
    ByPrimaryKey
    -0.46
    GetEnumerator
    -0.46
    POSITIVE LOGITS
     jspb
    0.66
     ComVisible
    0.64
     jsPsych
    0.60
     للمعارف
    0.60
    derive
    0.58
     فريبيس
    0.58
     contextLoads
    0.57
     EconPapers
    0.54
     octaves
    0.54
    InjectAttribute
    0.54
    Activations Density 3.896%

    No Known Activations