© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15411
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and formulas

    oai_token-act-pair · gemini-2.0-flash

    math/code

    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
    MigrationBuilder
    -0.66
     ExecuteAsync
    -0.61
    ########.
    -0.59
    sidemargin
    -0.59
     nonatomic
    -0.59
    __":
    -0.57
     himo
    -0.56
    </blockquote>
    -0.56
     ویکی‌پدیا
    -0.55
    ";
    -0.54
    POSITIVE LOGITS
     \
    1.01
    TableAdapter
    0.66
    ♥♥
    0.62
     ioutil
    0.59
    ()"
    0.55
     Beller
    0.54
    SharedCtor
    0.52
    vably
    0.50
     Перейти
    0.50
    "
    0.48
    Activations Density 2.842%

    No Known Activations