© 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. 10948
    Prev
    Next
    INDEX
    Explanations

    words that end with "er" or denote professional or theoretical fields, such as history or science

    oai_token-act-pair · gemini-2.0-flash

    comparative adjectives

    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
     higher
    -0.70
     younger
    -0.70
     safer
    -0.70
    higher
    -0.69
     firmer
    -0.67
    smaller
    -0.67
     faster
    -0.65
     brighter
    -0.63
     smaller
    -0.63
     happier
    -0.62
    POSITIVE LOGITS
     فريبيس
    0.87
    хьтан
    0.75
    XmlAccessType
    0.71
     Exactos
    0.69
     مشين
    0.68
    twimg
    0.67
     <>",
    0.67
     gawas
    0.62
     незавершена
    0.62
    copg
    0.61
    Activations Density 15.110%

    No Known Activations