© 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. 15027
    Prev
    Next
    INDEX
    Explanations

    words or phrases that subjectively evaluate a situation or research finding

    oai_token-act-pair · gemini-2.0-flash

    from

    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
     autorytatywna
    -0.84
     kasarigan
    -0.73
    انيف
    -0.72
    ContentAsync
    -0.70
    expandindo
    -0.69
     ModelExpression
    -0.67
    invokeLater
    -0.65
    WebServlet
    -0.65
     kaarangay
    -0.63
     cherchés
    -0.63
    POSITIVE LOGITS
     from
    2.72
    from
    2.17
     FROM
    1.93
     From
    1.89
    From
    1.85
     från
    1.70
     dari
    1.70
    จาก
    1.66
    从
    1.64
    FROM
    1.63
    Activations Density 4.363%

    No Known Activations