© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8039
    Prev
    Next
    INDEX
    Explanations

    words associated with physical location

    oai_token-act-pair · gemini-2.0-flash

    Hidden location

    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
    IndentedString
    -0.67
     noDo
    -0.64
    HasAnnotation
    -0.63
    +#+
    -0.63
    PropertyChanging
    -0.60
    fjspx
    -0.60
     contextLoads
    -0.59
    AccessorTable
    -0.58
    StringCopy
    -0.57
    MigrationBuilder
    -0.57
    POSITIVE LOGITS
     hidden
    0.92
     inaccessible
    0.82
    Hidden
    0.78
     protected
    0.77
    hidden
    0.76
     concealed
    0.73
     tucked
    0.72
     sheltered
    0.72
     visible
    0.71
     oculta
    0.71
    Activations Density 0.998%

    No Known Activations