© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6202
    Prev
    Next
    INDEX
    Explanations

    the string "Ep", sometimes followed by other letters

    oai_token-act-pair · gemini-2.0-flash

    Medical, chemical contexts with "Ep/Dep"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    awtextra
    -0.87
    GEBURTSDATUM
    -0.84
    NameInMap
    -0.83
    Hozzáférés
    -0.79
    AsUp
    -0.78
    setVerticalGroup
    -0.73
    DeleteBehavior
    -0.72
     ProtoMessage
    -0.71
    DotNetBar
    -0.71
    addCriterion
    -0.68
    POSITIVE LOGITS
     تضيفلها
    0.51
     ajudá
    0.44
    __*/
    0.43
    følgelig
    0.42
    SharedCtor
    0.42
    -------
    0.41
    ához
    0.41
     SOS
    0.41
    SOS
    0.40
     enää
    0.39
    Activations Density 0.472%

    No Known Activations