© 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. 10063
    Prev
    Next
    INDEX
    Explanations

    words and phrases from scientific documents regarding animal testing, living conditions, and excretions.

    oai_token-act-pair · gemini-2.0-flash

    animal care

    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
     hùng
    -0.48
    lass
    -0.45
    štu
    -0.44
     insec
    -0.43
    CUSS
    -0.43
    gazette
    -0.43
     ویکی‌آمباردا
    -0.43
    covo
    -0.42
    viertel
    -0.42
    tagHelperRunner
    -0.42
    POSITIVE LOGITS
    CppCodeGen
    0.87
     calldata
    0.70
    IsContent
    0.69
    setVerticalGroup
    0.68
    PasswordEncoder
    0.67
    usermodel
    0.62
     NSCoder
    0.61
     cages
    0.59
    WireFormatLite
    0.59
    存于互联网档案馆
    0.59
    Activations Density 0.787%

    No Known Activations