© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10045
    Prev
    Next
    INDEX
    Explanations

    words and abbreviations associated with legal and scientific documents

    oai_token-act-pair · gemini-2.0-flash

    legal and public profile

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.64
     autorytatywna
    -0.63
    }}^{(
    -0.60
    WebElementEntity
    -0.55
    joueurs
    -0.54
     esternos
    -0.54
     مشارکت‌کنندگان
    -0.54
    argout
    -0.52
    BeginContext
    -0.52
     AppCompatTheme
    -0.52
    POSITIVE LOGITS
    <bos>
    0.67
     bø
    0.65
     tempio
    0.60
    SuppressLint
    0.56
     vegetación
    0.56
     felizes
    0.56
     createState
    0.55
     cappello
    0.54
     dangereux
    0.54
    Przypisy
    0.54
    Activations Density 1.554%

    No Known Activations