© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8185
    Prev
    Next
    INDEX
    Explanations

    descriptions of negative sentiment towards authority figures or institutions

    oai_token-act-pair · gemini-2.0-flash

    airport security

    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
    <bos>
    -0.54
    UnusedPrivate
    -0.54
    PreferredItem
    -0.50
     useCallback
    -0.49
    adə
    -0.48
     ơn
    -0.46
    CardHeader
    -0.46
    劾
    -0.44
    #+#
    -0.44
    عم
    -0.43
    POSITIVE LOGITS
     TSA
    0.83
    Geplaatst
    0.81
     screening
    0.79
     security
    0.75
    TSA
    0.72
     screenings
    0.70
     Checkpoint
    0.69
     oprot
    0.69
    Security
    0.66
     patted
    0.66
    Activations Density 1.327%

    No Known Activations