© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5447
    Prev
    Next
    INDEX
    Explanations

    the word "corner"

    oai_token-act-pair · gemini-2.0-flash

    corner

    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
     μην
    -0.68
     cytoplasm
    -0.67
     nationaux
    -0.63
     LCCN
    -0.63
     scarves
    -0.62
     wikipagina
    -0.60
     caliper
    -0.60
     kirja
    -0.60
     scolaire
    -0.60
     נוספת
    -0.59
    POSITIVE LOGITS
     تضيفلها
    1.02
    ChildScrollView
    1.01
     المعيارى
    0.91
    verwijspagina
    0.90
     estekak
    0.88
     متعلقه
    0.84
     utafitiHapana
    0.84
     jspb
    0.82
    StructEnd
    0.81
    Hozzáférés
    0.81
    Activations Density 1.009%

    No Known Activations