© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10914
    Prev
    Next
    INDEX
    Explanations

    gibberish and location info

    oai_token-act-pair · gemini-2.0-flash

    Balkans

    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
    ]-->
    -0.63
    niająca
    -0.61
     الرياضيه
    -0.61
     Oester
    -0.60
    قایناق‌لار
    -0.59
     didst
    -0.58
     JOptionPane
    -0.57
    Biographie
    -0.55
     propOrder
    -0.55
     فريبيس
    -0.54
    POSITIVE LOGITS
    IntoConstraints
    0.54
    queous
    0.54
    ves
    0.51
     Paglinawan
    0.49
    toBeDefined
    0.47
    xae
    0.47
    unshift
    0.46
    pytest
    0.45
     solares
    0.44
    ocer
    0.44
    Activations Density 0.122%

    No Known Activations