© 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. 9227
    Prev
    Next
    INDEX
    Explanations

    references to real-world locations, place names, or common nouns associated with physical places on maps

    oai_token-act-pair · gemini-2.0-flash

    location/area

    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
     NUKAT
    -0.78
    AndEndTag
    -0.71
    IntoConstraints
    -0.71
     propOrder
    -0.71
    TagMode
    -0.68
    __":
    -0.64
     &___
    -0.64
    DockStyle
    -0.63
     }{@
    -0.63
    SequentialGroup
    -0.62
    POSITIVE LOGITS
    iseries
    0.47
    .
    0.46
    ть
    0.46
    l
    0.46
    äuser
    0.46
    Stages
    0.44
    écuter
    0.44
    ラク
    0.44
     containing
    0.44
    containing
    0.43
    Activations Density 6.948%

    No Known Activations