© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10677
    Prev
    Next
    INDEX
    Explanations

    the word "of", especially when surrounded by legal or academic language

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    RegressionTest
    -0.96
    windowFixed
    -0.91
    GEBURTSDATUM
    -0.88
    +#+#
    -0.86
    Datuak
    -0.82
     مرئيه
    -0.81
    évaluateur
    -0.81
     ujednoznacz
    -0.78
    lgari
    -0.77
    Personendaten
    -0.76
    POSITIVE LOGITS
     of
    3.05
     của
    1.59
    ของ
    1.55
    of
    1.52
     Of
    1.17
    Of
    1.16
    ofthe
    1.10
     ofthe
    1.10
     OF
    1.03
     ของ
    1.00
    Activations Density 6.907%

    No Known Activations