© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9791
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially personal names, within a given text

    oai_token-act-pair · gemini-2.0-flash

    proper nouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Corintios
    -0.58
    ()]);
    -0.53
    ]]]
    -0.52
    °)
    -0.51
     Dernière
    -0.49
     propOrder
    -0.49
    "]();
    -0.48
    ^)
    -0.48
    "}},
    -0.48
    hoga
    -0.48
    POSITIVE LOGITS
    <bos>
    0.79
     ſte
    0.64
     estekak
    0.62
     ſta
    0.60
     pleaſure
    0.59
    :][
    0.59
    Попис
    0.59
     gemeint
    0.57
    ؤية
    0.57
    bootstrapcdn
    0.57
    Activations Density 10.708%

    No Known Activations