© 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. 11095
    Prev
    Next
    INDEX
    Explanations

    the word "appear" and its variants

    oai_token-act-pair · gemini-2.0-flash

    appear

    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
     Inscrivez
    -0.65
     appears
    -0.62
     consom
    -0.57
     metav
    -0.57
     squarely
    -0.57
    ंदीखरीदारी
    -0.56
    gory
    -0.56
     hiz
    -0.56
    elock
    -0.56
    ScopeManager
    -0.55
    POSITIVE LOGITS
     souhaitent
    0.70
    bentukan
    0.62
    UnusedPrivate
    0.61
    FieldBuilder
    0.60
     Mika
    0.59
    <bos>
    0.59
     auftreten
    0.58
     altında
    0.57
    ✭✭
    0.57
     ontwikkeling
    0.57
    Activations Density 1.493%

    No Known Activations