© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13429
    Prev
    Next
    INDEX
    Explanations

    the word violations or other legal terms involving legal processes

    oai_token-act-pair · gemini-2.0-flash

    violation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     violation
    -0.92
    violation
    -0.77
     violating
    -0.75
     violated
    -0.71
     Violation
    -0.71
    protoimpl
    -0.69
    yntaxException
    -0.69
     offense
    -0.68
     violations
    -0.68
    NavController
    -0.67
    POSITIVE LOGITS
     Muck
    0.64
    IndentedString
    0.60
     خاص
    0.56
    WSGI
    0.55
     whiteColor
    0.54
    )="
    0.53
    )?;
    0.52
     Swit
    0.50
     '.';
    0.50
    Empire
    0.50
    Activations Density 7.882%

    No Known Activations