© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4735
    Prev
    Next
    INDEX
    Explanations

    phrases where a person or people are put at a physical or emotional disadvantage

    oai_token-act-pair · gemini-2.0-flash

    vulnerability

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    GEBURTSDATUM
    -0.80
    MessageOf
    -0.77
    AddHtmlAttribute
    -0.69
    ագրություններ
    -0.64
    ScopeManager
    -0.63
    SequentialGroup
    -0.61
    HideFlags
    -0.60
    offsetof
    -0.60
    ChildScrollView
    -0.60
     للمعارف
    -0.59
    POSITIVE LOGITS
     susceptible
    0.96
     susceptibility
    0.95
     prone
    0.95
     vulnerable
    0.94
     vulnerability
    0.93
     opportunities
    0.92
     opportunity
    0.92
    opportunity
    0.82
     Vulnerability
    0.79
     peluang
    0.79
    Activations Density 1.644%

    No Known Activations