© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13545
    Prev
    Next
    INDEX
    Explanations

    words related to lawsuits, complaints, and legal proceedings (like trials and appeals) involving people and organizations.

    oai_token-act-pair · gemini-2.0-flash

    Legal/political issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     AssemblyCulture
    -0.57
     ligiloj
    -0.56
     estekak
    -0.55
     Вікі
    -0.52
    DrawerToggle
    -0.51
    CodeAttribute
    -0.49
    AndEndTag
    -0.48
    GraphicsUnit
    -0.46
    cshtml
    -0.44
    AutoScale
    -0.44
    POSITIVE LOGITS
    Демографія
    0.53
    ^(@)
    0.52
    .")]
    0.50
    帖最后由
    0.50
    andet
    0.49
     дописавши
    0.47
    NUMX
    0.45
     hinweg
    0.44
    })*/
    0.44
     organisers
    0.44
    Activations Density 1.576%

    No Known Activations