© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10377
    Prev
    Next
    INDEX
    Explanations

    words that are likely to be in a mathematical or academic paper and proper nouns from what reads like a fantasy novel

    oai_token-act-pair · gemini-2.0-flash

    take/taking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    GraphicsUnit
    -0.77
    MarshalTo
    -0.66
     Infórmanos
    -0.66
    utilisons
    -0.64
    CloseOperation
    -0.62
    )++;
    -0.60
     ویکی‌پدی
    -0.59
    makeConstraints
    -0.59
    DoubleQuotes
    -0.58
     oprot
    -0.58
    POSITIVE LOGITS
     take
    2.13
    take
    2.09
     takes
    2.02
     taking
    2.00
    Take
    1.98
     Take
    1.95
    Taking
    1.93
    takes
    1.91
    taking
    1.89
     Taking
    1.87
    Activations Density 4.825%

    No Known Activations