© 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. 830
    Prev
    Next
    INDEX
    Explanations

    the word "on" when used as a preposition.

    oai_token-act-pair · gemini-2.0-flash

    on

    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
    stylesheet
    -0.56
    <bos>
    -0.56
    ThemeOverlay
    -0.47
    On
    -0.46
    Datuak
    -0.46
     on
    -0.45
    modium
    -0.44
    lander
    -0.41
     On
    -0.41
    Cuánto
    -0.40
    POSITIVE LOGITS
    StructEnd
    0.70
     Chwiliwch
    0.68
     المعيارى
    0.65
     estekak
    0.64
    ftagPool
    0.63
    pexpr
    0.63
     متعلقه
    0.63
     Paglinawan
    0.62
     iprot
    0.61
     Wicidata
    0.61
    Activations Density 3.758%

    No Known Activations