© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3516
    Prev
    Next
    INDEX
    Explanations

    mathematical problems and their attempted solutions or related questions about problem assistance.

    oai_token-act-pair · gemini-2.0-flash

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    Autoritní
    -1.04
     resourceCulture
    -0.98
     ویکی‌پدی
    -0.90
    دانشنامهٔ
    -0.89
    RegressionTest
    -0.84
    ніципа
    -0.82
     Italijanski
    -0.79
    ########.
    -0.77
    DeleteBehavior
    -0.76
    Portály
    -0.76
    POSITIVE LOGITS
    🐋
    0.42
     Envío
    0.39
     još
    0.39
    Transkript
    0.38
     Arxivat
    0.38
    π
    0.38
    var
    0.37
     万
    0.36
     transmisión
    0.36
     transmissão
    0.36
    Activations Density 3.234%

    No Known Activations