© 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. 4510
    Prev
    Next
    INDEX
    Explanations

    the phrase "New York City" and the word "Inventors."

    oai_token-act-pair · gemini-2.0-flash

    City

    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
     of
    -0.87
     in
    -0.83
     an
    -0.82
     a
    -0.75
     and
    -0.73
     is
    -0.71
     I
    -0.71
     we
    -0.70
     there
    -0.68
     as
    -0.67
    POSITIVE LOGITS
    NameInMap
    1.35
     jScrollPane
    1.16
     Theſe
    1.12
     Económica
    1.09
     pleaſure
    1.07
     saites
    1.06
     ſeveral
    1.04
    TagMode
    1.04
     ſtate
    1.03
    Personendaten
    1.03
    Activations Density 0.221%

    No Known Activations