© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7799
    Prev
    Next
    INDEX
    Explanations

    mentions of American football and also medical terms

    oai_token-act-pair · gemini-2.0-flash

    Medical related texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    addCriterion
    -0.69
     Audiodateien
    -0.64
     لينك
    -0.61
    #+#
    -0.57
     forKey
    -0.57
    OrBuilder
    -0.57
    viewDidLoad
    -0.55
    onAttach
    -0.54
     يتيمه
    -0.54
    asuring
    -0.54
    POSITIVE LOGITS
     Pop
    0.51
     opening
    0.49
     Paglinawan
    0.49
    旺
    0.48
    Opening
    0.48
     POP
    0.47
     Opening
    0.47
     Driving
    0.47
    戴
    0.46
    Pop
    0.46
    Activations Density 0.683%

    No Known Activations