© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12843
    Prev
    Next
    INDEX
    Explanations

    instances where someone is granted access to information

    oai_token-act-pair · gemini-2.0-flash

    terms related to notice and notification

    np_token-act-pair-logits · gpt-4o-mini

    notice, warning

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     palmas
    -0.50
    onOptions
    -0.48
    TestRunner
    -0.47
    URLException
    -0.47
     Audiodateien
    -0.46
    urlencoded
    -0.46
     estimés
    -0.45
    ançon
    -0.42
    Населення
    -0.42
    ruch
    -0.42
    POSITIVE LOGITS
     notice
    1.77
     warning
    1.46
     Notice
    1.42
    notice
    1.41
     notification
    1.38
    Notice
    1.31
     NOTICE
    1.29
     notices
    1.27
     alert
    1.23
    NOTICE
    1.20
    Activations Density 2.523%

    No Known Activations