© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15649
    Prev
    Next
    INDEX
    Explanations

    numerical values, especially percentages and those related to medical statistics

    oai_token-act-pair · gemini-2.0-flash

    percentages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     sujetos
    -0.43
     cost
    -0.42
    impos
    -0.41
    当
    -0.41
     häl
    -0.41
    issimo
    -0.40
     der
    -0.40
    ’
    -0.40
    вата
    -0.38
     Construction
    -0.36
    POSITIVE LOGITS
    archiviato
    0.83
     وتسجيلات
    0.80
    DockStyle
    0.77
    StoryboardSegue
    0.74
     дописавши
    0.73
    存于互联网档案馆
    0.73
    出版年
    0.71
    esgue
    0.71
    참고
    0.71
     سكانية
    0.71
    Activations Density 24.943%

    No Known Activations