© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2747
    Prev
    Next
    INDEX
    Explanations

    the start of the word "Confederation" or words starting with "Conf"

    oai_token-act-pair · gemini-2.0-flash

    conf

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    atsby
    -0.60
    GenerationType
    -0.59
    árol
    -0.56
    ConfigureAwait
    -0.53
    XCT
    -0.53
    ]--;
    -0.53
    ともに
    -0.52
    oodle
    -0.52
    ább
    -0.52
     Hongrie
    -0.52
    POSITIVE LOGITS
    Lähteet
    0.57
     TextAppearance
    0.56
    AddHtmlAttribute
    0.49
    таратура
    0.47
    FieldNumber
    0.46
     ilma
    0.46
    AsUp
    0.45
    windowFixed
    0.44
     الحره
    0.42
     BIBSYS
    0.42
    Activations Density 0.354%

    No Known Activations