© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13746
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to medical malpractice and injuries, particularly spinal injuries, within the context of legal or medical documents

    oai_token-act-pair · gemini-2.0-flash

    injury

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    IUrlHelper
    -0.60
    TestBed
    -0.52
     desp
    -0.50
    TypedDataSet
    -0.50
     Tron
    -0.49
    MigrationBuilder
    -0.49
     dét
    -0.49
    <bos>
    -0.49
    webElementXpaths
    -0.48
    phemy
    -0.47
    POSITIVE LOGITS
     CreateTagHelper
    0.77
     MainAxisSize
    0.74
    ArgsConstructor
    0.73
    Према
    0.71
    ագրություններ
    0.68
    脚注の使い方
    0.65
     initComponents
    0.65
     typelib
    0.59
    BeforeClass
    0.57
     useStyles
    0.56
    Activations Density 1.328%

    No Known Activations