© 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. 13667
    Prev
    Next
    INDEX
    Explanations

    the word "hold" followed by prepositions like "on" or "out", possibly indicating phrases involving retention or resistance.

    oai_token-act-pair · gemini-2.0-flash

    hold

    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
     hold
    -1.67
    hold
    -1.52
     Hold
    -1.50
     holding
    -1.48
    Hold
    -1.45
     holds
    -1.41
    Holding
    -1.38
     held
    -1.38
     Holding
    -1.38
     HOLD
    -1.34
    POSITIVE LOGITS
    GEBURTSDATUM
    0.63
    EndGlobalSection
    0.61
    Pautan
    0.59
    runApp
    0.59
    onViewCreated
    0.58
     jsPsych
    0.57
     Rtl
    0.56
     سكانية
    0.56
    RTEE
    0.55
    Inggris
    0.54
    Activations Density 1.201%

    No Known Activations