© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1059
    Prev
    Next
    INDEX
    Explanations

    the word "a" followed by words related to properties or vocations

    oai_token-act-pair · gemini-2.0-flash

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    <bos>
    -0.92
    ArrowToggle
    -0.69
     a
    -0.62
     an
    -0.59
     estekak
    -0.56
     is
    -0.44
    is
    -0.43
     tunggal
    -0.41
    ="#"><
    -0.41
     
    -0.41
    POSITIVE LOGITS
    actéristique
    0.71
     للاسماء
    0.66
     PROCED
    0.65
    Sklici
    0.65
    INFL
    0.64
     chopsticks
    0.64
     snippetHide
    0.64
     Hered
    0.63
    kuuta
    0.63
    usercontent
    0.63
    Activations Density 3.165%

    No Known Activations