© 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. 3893
    Prev
    Next
    INDEX
    Explanations

    a wide variety of named entities, including people, places, organizations, and events, and sometimes does so imperfectly

    oai_token-act-pair · gemini-2.0-flash

    king/queen

    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
     AssemblyCompany
    -0.81
    RectangleBorder
    -0.77
     ویکی‌پدی
    -0.75
     виправивши
    -0.73
    InputBorder
    -0.73
     Савезне
    -0.71
    URLException
    -0.69
    disposing
    -0.69
    BufferException
    -0.68
    addCriterion
    -0.66
    POSITIVE LOGITS
     king
    2.02
     queen
    1.74
     King
    1.70
     kings
    1.58
    King
    1.53
     KING
    1.51
     Queen
    1.49
    Queen
    1.40
    queen
    1.38
     QUEEN
    1.33
    Activations Density 1.623%

    No Known Activations