© 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. 7506
    Prev
    Next
    INDEX
    Explanations

    tokens related to the state and economy

    oai_token-act-pair · gemini-2.0-flash

    s

    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
    <bos>
    -0.54
     vuitton
    -0.52
    principalTable
    -0.48
    InteropServices
    -0.46
    worth
    -0.44
     Investigaciones
    -0.43
    θεν
    -0.42
    GeoNames
    -0.42
    Curl
    -0.41
    Assertions
    -0.41
    POSITIVE LOGITS
     betweenstory
    0.66
    /**
    0.64
    
    0.58
    parsedMessage
    0.58
    StoryboardSegue
    0.55
    toggler
    0.54
     "..\..\..\
    0.54
    帖最后由
    0.53
    NameInMap
    0.53
     "..\..\
    0.53
    Activations Density 6.326%

    No Known Activations