© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10584
    Prev
    Next
    INDEX
    Explanations

    the word "safe"

    oai_token-act-pair · gemini-2.0-flash

    safe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     safe
    -1.05
    safe
    -0.88
     safely
    -0.77
     safety
    -0.71
    safety
    -0.71
     unsafe
    -0.71
    ulario
    -0.70
     surla
    -0.69
    vron
    -0.66
    ectl
    -0.66
    POSITIVE LOGITS
    thâu
    0.73
     Offisielt
    0.62
    Fig
    0.61
    робнее
    0.59
     laman
    0.58
     '';
    0.57
     Dorsal
    0.56
     FIG
    0.56
    ...";
    0.56
    FIG
    0.55
    Activations Density 0.875%

    No Known Activations