© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1957
    Prev
    Next
    INDEX
    Explanations

    phrases that give a warning or advice

    oai_token-act-pair · gemini-2.0-flash

    cautionary keywords related to vigilance

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

    caution

    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
     EconPapers
    -0.83
     pinulongan
    -0.76
    Personendaten
    -0.74
    /*
    -0.65
    InvalidProtocol
    -0.64
    #
    -0.63
    참고
    -0.61
    ✨:
    -0.60
     createState
    -0.60
     onCreateView
    -0.59
    POSITIVE LOGITS
     watch
    0.89
    Watch
    0.77
     Watch
    0.77
    watch
    0.77
     guard
    0.77
     WATCH
    0.73
     watches
    0.67
     watchman
    0.66
     careful
    0.65
    Guard
    0.63
    Activations Density 1.768%

    No Known Activations