© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7026
    Prev
    Next
    INDEX
    Explanations

    language often appearing in a medical case study or report

    oai_token-act-pair · gemini-2.0-flash

    report

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    そ
    -0.44
    []
    -0.43
     плоско
    -0.42
    Mode
    -0.41
    ತ್
    -0.41
     dry
    -0.40
    íssimo
    -0.40
    odeon
    -0.40
    coop
    -0.39
    CPtr
    -0.39
    POSITIVE LOGITS
    AutoresizingMask
    1.16
    +#+#
    0.79
    AddTagHelper
    0.75
     useState
    0.75
    useState
    0.74
    CGRectMake
    0.73
     وتسجيلات
    0.73
    complexContent
    0.73
    tagHelperRunner
    0.73
     useRef
    0.72
    Activations Density 1.573%

    No Known Activations