© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3009
    Prev
    Next
    INDEX
    Explanations

    the word "goods", sometimes it finds " case", "South", or "Miss"

    oai_token-act-pair · gemini-2.0-flash

    goods

    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
    Negative Logits
     the
    -0.80
     various
    -0.65
     specialising
    -0.65
     pelbagai
    -0.63
     specialised
    -0.61
     ‘
    -0.61
    liesslich
    -0.60
     specialise
    -0.60
     '
    -0.59
     several
    -0.59
    POSITIVE LOGITS
    parsedMessage
    0.86
    +#+#
    0.86
    )))));
    0.82
    ">//
    0.81
    RegressionTest
    0.79
    RectangleBorder
    0.77
    NameInMap
    0.76
    contentLoaded
    0.75
    MigrationBuilder
    0.75
    RenderAtEndOf
    0.73
    Activations Density 1.890%

    No Known Activations