© 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. 15711
    Prev
    Next
    INDEX
    Explanations

    information about museums, especially those that are new, expanded, or undergoing updates

    oai_token-act-pair · gemini-2.0-flash

    museum exhibits

    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
    Spoljašnje
    -0.40
     Distrikt
    -0.39
    __(/*!
    -0.39
    nom
    -0.38
     strass
    -0.37
    ServiceClient
    -0.37
    mopolitan
    -0.37
    fazione
    -0.36
    /**
    -0.36
    ENTY
    -0.35
    POSITIVE LOGITS
     exhibit
    1.04
     exhibits
    1.02
     visitor
    1.01
     Exhibits
    1.01
     Exhibit
    0.93
     visitors
    0.93
     Visitor
    0.92
     Collections
    0.92
    Exhibit
    0.91
    Interpretation
    0.90
    Activations Density 2.664%

    No Known Activations