© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12004
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to negative feelings and safety

    oai_token-act-pair · gemini-2.0-flash

    scared

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     effray
    -0.99
     scary
    -0.80
     scared
    -0.80
    zzleHttp
    -0.79
     terrified
    -0.79
    scary
    -0.77
     scares
    -0.76
    seamnă
    -0.74
     chré
    -0.73
    gonic
    -0.73
    POSITIVE LOGITS
    <bos>
    0.75
    ability
    0.53
    SourceChecksum
    0.51
    <tr>
    0.50
    '
    0.48
    try
    0.47
    عف
    0.46
    import
    0.42
    fahan
    0.41
     using
    0.40
    Activations Density 2.043%

    No Known Activations