© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10602
    Prev
    Next
    INDEX
    Explanations

    words ending in "s" that are often, but not always, proper nouns or plural

    oai_token-act-pair · gemini-2.0-flash

    neurons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     PLWABN
    -0.64
    Kjelder
    -0.63
     Wikimédia
    -0.61
     незавершена
    -0.59
    rrggbb
    -0.59
     ویکی‌پدیا
    -0.57
    Hauptartikel
    -0.57
    niająca
    -0.56
     resourceCulture
    -0.56
     kautta
    -0.56
    POSITIVE LOGITS
    <bos>
    0.84
     tenth
    0.66
    iels
    0.57
    XmlAccessorType
    0.54
     fifth
    0.54
     ten
    0.53
     good
    0.53
     fourth
    0.53
    mec
    0.52
     fourteenth
    0.52
    Activations Density 0.488%

    No Known Activations