© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13451
    Prev
    Next
    INDEX
    Explanations

    text related to fighting or combat and magic

    oai_token-act-pair · gemini-2.0-flash

    Fighting moves

    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
     للاسماء
    -0.79
    RenderAtEndOf
    -0.75
    Datuak
    -0.69
    mergeFrom
    -0.69
     AssemblyTitle
    -0.66
    opensource
    -0.64
     romantique
    -0.62
     jScrollPane
    -0.61
    adget
    -0.61
     NSCoder
    -0.61
    POSITIVE LOGITS
     casting
    0.61
     cast
    0.57
     par
    0.56
     swings
    0.54
    casts
    0.52
    casting
    0.52
    Cast
    0.50
     swing
    0.50
     dod
    0.49
     duck
    0.48
    Activations Density 1.579%

    No Known Activations