© 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. 8078
    Prev
    Next
    INDEX
    Explanations

    explicit dates, especially when separated by hyphens or slashes

    oai_token-act-pair · gemini-2.0-flash

    months

    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
     four
    -0.72
     FIVE
    -0.69
    Four
    -0.68
     five
    -0.68
    Three
    -0.68
    Five
    -0.67
    four
    -0.67
     Three
    -0.67
     FOUR
    -0.66
     Four
    -0.66
    POSITIVE LOGITS
    Personendaten
    0.64
     sixty
    0.60
     myſelf
    0.58
     itſelf
    0.57
     <=",
    0.57
    TagMode
    0.56
     Sixty
    0.56
     الرياضيه
    0.55
     Reſ
    0.54
     eighty
    0.54
    Activations Density 5.947%

    No Known Activations