© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7031
    Prev
    Next
    INDEX
    Explanations

    references to law enforcement agencies or officers

    oai_token-act-pair · gemini-2.0-flash

    law enforcement offices

    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
     viện
    -0.43
    GHIJKLM
    -0.41
     centre
    -0.40
     japonica
    -0.39
    MUST
    -0.39
     center
    -0.39
    srcs
    -0.38
     سبورت
    -0.38
    居
    -0.36
    ielder
    -0.36
    POSITIVE LOGITS
    ThroughAttribute
    0.86
    aarrggbb
    0.78
    DrawerToggle
    0.72
    новниш
    0.70
     beginnetje
    0.68
    +#+#
    0.68
    complexType
    0.67
    DeleteBehavior
    0.67
    ViewFeatures
    0.66
    awtextra
    0.63
    Activations Density 0.669%

    No Known Activations