© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14945
    Prev
    Next
    INDEX
    Explanations

    the word "of" (case insensitive), sometimes with some preference for capitalization.

    oai_token-act-pair · gemini-2.0-flash

    Of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ly
    -0.85
    ed
    -0.73
    of
    -0.69
    es
    -0.69
    ↵
    -0.68
    <b>
    -0.66
    l
    -0.64
    Of
    -0.63
    0
    -0.62
      
    -0.61
    POSITIVE LOGITS
     typelib
    1.43
    EDEFAULT
    1.38
    SharedDtor
    1.28
     مرئيه
    1.27
     ويكيميديا
    1.27
     виправивши
    1.26
    Personendaten
    1.26
     Roskov
    1.24
     disambiguazione
    1.24
    featureID
    1.24
    Activations Density 1.647%

    No Known Activations