© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2013
    Prev
    Next
    INDEX
    Explanations

    mentions of the architecture or structure of buildings and the political entities involved in them

    oai_token-act-pair · gemini-2.0-flash

    inside, internal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ImageContext
    -0.66
    ConstraintMaker
    -0.64
    ButterKnife
    -0.62
    primento
    -0.61
    HasAnnotation
    -0.61
    Tracce
    -0.61
     ankles
    -0.59
     contextLoads
    -0.57
     @"/
    -0.57
     censiti
    -0.57
    POSITIVE LOGITS
     inside
    1.95
     internal
    1.88
    inside
    1.73
     interior
    1.73
    internal
    1.72
     Inside
    1.68
    Inside
    1.66
     internally
    1.66
     outside
    1.60
    Internal
    1.58
    Activations Density 1.006%

    No Known Activations