© 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. 2752
    Prev
    Next
    INDEX
    Explanations

    text related to Kaseya VSA software and cybersecurity authentication

    oai_token-act-pair · gemini-2.0-flash

    administrative terms and jargon

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

    computer software

    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
    RegressionTest
    -0.78
     المعيارى
    -0.77
    IntoConstraints
    -0.69
     AssemblyProduct
    -0.63
    RectangleBorder
    -0.63
    NewReader
    -0.63
    WireFormatLite
    -0.62
    AndEndTag
    -0.61
     oprot
    -0.59
     nonatomic
    -0.57
    POSITIVE LOGITS
    ━━━
    0.56
    uper
    0.52
    SBS
    0.50
     amminist
    0.50
    splatz
    0.50
     administrativos
    0.50
     administratif
    0.49
     GPO
    0.49
    registry
    0.49
     expediente
    0.47
    Activations Density 1.580%

    No Known Activations