© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12957
    Prev
    Next
    INDEX
    Explanations

    parts of C code defining structures with bitfields and some code related to the mantis chip

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     kasarigan
    -0.73
    uttosto
    -0.69
     فريبيس
    -0.69
    Cari
    -0.66
     médicaux
    -0.64
    SPE
    -0.61
    Lähteet
    -0.60
     vectorielles
    -0.60
    enumi
    -0.60
    intenant
    -0.60
    POSITIVE LOGITS
    AndEndTag
    0.57
     disambiguazione
    0.54
    Gambas
    0.53
    ].(
    0.52
    openzeppelin
    0.48
    }}^{(
    0.48
     ویکی‌پدیا
    0.47
     Eleg
    0.46
     thoſe
    0.46
    Ching
    0.46
    Activations Density 2.733%

    No Known Activations