© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11594
    Prev
    Next
    INDEX
    Explanations

    French words or phrases related to technology and internet

    oai_token-act-pair · gemini-2.0-flash

    French

    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
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.85
     ModelExpression
    -0.83
     فريبيس
    -0.82
    ousands
    -0.82
    tableFuture
    -0.81
    abatic
    -0.81
    TargetException
    -0.79
    fjspx
    -0.77
     وتسجيلات
    -0.77
    HttpFoundation
    -0.74
    POSITIVE LOGITS
     is
    0.58
    by
    0.56
    Demografie
    0.55
    ,
    0.52
     en
    0.51
    One
    0.51
     One
    0.49
    BY
    0.47
    The
    0.47
     Elu
    0.47
    Activations Density 0.323%

    No Known Activations