© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 7971
    Prev
    Next
    INDEX
    Explanations

    mathematical equations, especially ones involving exponents, fractions, trigonometric functions (cos, sin), and the variable theta.

    oai_token-act-pair · gemini-2.0-flash

    ^

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     democrática
    -0.67
     Cosmopolitan
    -0.58
    tvguidetime
    -0.58
    asantry
    -0.57
    原始内容存档于
    -0.57
    biamo
    -0.56
     bienvenue
    -0.55
     vectorielles
    -0.55
    ponible
    -0.54
     zijne
    -0.54
    POSITIVE LOGITS
    });*/
    0.56
    şiv
    0.54
     />);
    0.50
    tub
    0.48
    };*/
    0.47
    :],
    0.46
     estekak
    0.46
    RefNanny
    0.46
    />";
    0.45
    %");
    0.45
    Activations Density 9.358%

    No Known Activations