© 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
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8071
    Prev
    Next
    INDEX
    Explanations

    code elements, especially those related to keys, paths, and boolean attributes

    oai_token-act-pair · gemini-2.0-flash

    Key

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     say
    -0.59
    tient
    -0.56
     تضيفلها
    -0.51
     Say
    -0.50
    reactstrap
    -0.50
    /__
    -0.49
     المعيارى
    -0.49
    chaff
    -0.47
                                  
    -0.47
     sorta
    -0.46
    POSITIVE LOGITS
    WebVitals
    0.86
     '\\;'
    0.85
    awtextra
    0.84
    exels
    0.75
     feroit
    0.75
    Datuak
    0.73
    balleur
    0.70
    ksom
    0.69
     betweenstory
    0.69
    MethodManager
    0.69
    Activations Density 1.727%

    No Known Activations