© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1277
    Prev
    Next
    INDEX
    Explanations

    the word "we", positive action verbs, and words demonstrating an eagerness to act

    oai_token-act-pair · gemini-2.0-flash

    risk

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    TypedDataSet
    -1.09
     ExecuteAsync
    -0.91
    WithIOException
    -0.78
     архивлан
    -0.74
     <>",
    -0.72
    ussis
    -0.71
     Infórmanos
    -0.70
    存于互联网档案馆
    -0.69
    StoryboardSegue
    -0.69
    HtmlAttribute
    -0.69
    POSITIVE LOGITS
     risk
    1.93
     Risk
    1.66
    risk
    1.66
     risks
    1.64
    Risk
    1.56
     RISK
    1.55
    RISK
    1.34
     risky
    1.34
     Risks
    1.32
     riesgo
    1.30
    Activations Density 0.561%

    No Known Activations