© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2151
    Prev
    Next
    INDEX
    Explanations

    mentions of economic concepts, locations in the USA, references to sources, and words hinting at government or medical roles.

    oai_token-act-pair · gemini-2.0-flash

    United States

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    initialise
    -0.92
     Whilst
    -0.86
    Whilst
    -0.85
    centre
    -0.85
    COLOUR
    -0.84
     characterised
    -0.84
     emphasise
    -0.82
     centre
    -0.82
     organisations
    -0.82
     colour
    -0.81
    POSITIVE LOGITS
     Și
    0.80
     favorably
    0.79
     labors
    0.78
    Și
    0.77
     harbor
    0.76
     parlor
    0.76
     flavorful
    0.75
     behaviors
    0.75
    ologic
    0.75
     theater
    0.73
    Activations Density 13.264%

    No Known Activations