© 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. 12597
    Prev
    Next
    INDEX
    Explanations

    geometry terms, particularly those involving circles and spheres

    oai_token-act-pair · gemini-2.0-flash

    shapes and geometry

    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
     diametro
    -0.86
     ainfi
    -0.73
    المناصب
    -0.70
     Durchmesser
    -0.68
     diameter
    -0.68
     círculo
    -0.68
     diamètre
    -0.67
     radii
    -0.66
     circle
    -0.66
    diameter
    -0.65
    POSITIVE LOGITS
     col
    0.52
     PeEnEo
    0.50
     stretch
    0.47
     Italijani
    0.46
    roit
    0.46
    ulong
    0.45
    icorn
    0.45
    IDATE
    0.44
     مشين
    0.44
     sust
    0.43
    Activations Density 15.364%

    No Known Activations