© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12545
    Prev
    Next
    INDEX
    Explanations

    mathematical problems that use words like "factor", "multiple", and "divide"

    oai_token-act-pair · gemini-2.0-flash

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    WithIOException
    -0.83
     Monfieur
    -0.74
     referenties
    -0.74
     fubject
    -0.72
     itſelf
    -0.72
     reaſon
    -0.70
     myſelf
    -0.70
     Anſ
    -0.69
     againſt
    -0.69
     Perfon
    -0.69
    POSITIVE LOGITS
    amento
    0.47
    ULDER
    0.45
    верное
    0.43
    urement
    0.42
    amentos
    0.42
    \/
    0.42
    öö
    0.42
     Ak
    0.40
     dever
    0.40
    auer
    0.40
    Activations Density 1.209%

    No Known Activations