© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1658
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the allocation and utilization of resources, particularly in the context of funding, computing, and storage

    oai_token-act-pair · gemini-2.0-flash

    words related to system overload or strain

    np_token-act-pair-logits · gpt-4o-mini

    overloaded

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    /**
    -0.62
    IsMutable
    -0.57
    VIAF
    -0.56
    __':
    -0.53
    RenderAtEndOf
    -0.52
     فريبيس
    -0.52
    GEBURTSDATUM
    -0.52
    Personensuche
    -0.51
    offsetof
    -0.49
    LEADING
    -0.49
    POSITIVE LOGITS
    OGND
    0.72
     виправивши
    0.62
     stretched
    0.59
     overburden
    0.56
     overwhelmed
    0.54
     géographie
    0.52
    stretched
    0.52
     Lightboxes
    0.52
     paraly
    0.50
     overloaded
    0.49
    Activations Density 3.422%

    No Known Activations