© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12113
    Prev
    Next
    INDEX
    Explanations

    phrases related to patents, especially phrases including "formed" or "mounted"

    oai_token-act-pair · gemini-2.0-flash

    Describing formation/extension

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ixel
    -0.50
    ]='\
    -0.50
     Visual
    -0.50
     lenker
    -0.49
    риф
    -0.49
    UAL
    -0.49
     True
    -0.48
    urar
    -0.47
    acco
    -0.47
    UFF
    -0.47
    POSITIVE LOGITS
    <bos>
    1.21
     PLWABN
    0.70
    InjectAttribute
    0.67
    Geplaatst
    0.63
    はじめに
    0.63
    السكان
    0.60
    AddTagHelper
    0.60
     ModelExpression
    0.59
     indisponible
    0.58
    TagMode
    0.57
    Activations Density 3.585%

    No Known Activations