© 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. 7637
    Prev
    Next
    INDEX
    Explanations

    CSS and XML code related to aligning text to the left, and some HTML tags

    oai_token-act-pair · gemini-2.0-flash

    text alignment

    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
    UnknownFields
    -0.60
     loob
    -0.56
     fubject
    -0.54
     subject
    -0.49
     hangers
    -0.49
    setSubject
    -0.48
    Activité
    -0.46
     marinho
    -0.45
     topic
    -0.45
    teza
    -0.45
    POSITIVE LOGITS
    DockStyle
    0.79
    IntoConstraints
    0.73
     align
    0.68
     center
    0.64
     Align
    0.64
    align
    0.62
    Align
    0.62
     justify
    0.61
     Мексичка
    0.60
     aligned
    0.60
    Activations Density 0.911%

    No Known Activations