© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14724
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal proceedings, judgements, or regulations, especially when something is deemed inappropriate.

    oai_token-act-pair · gemini-2.0-flash

    legality/appropriateness

    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
     proper
    -0.57
     missing
    -0.57
     correct
    -0.57
     adequacy
    -0.56
     properly
    -0.56
     Incorrect
    -0.56
     đúng
    -0.55
     prawidł
    -0.54
     mancanza
    -0.54
    Incorrect
    -0.54
    POSITIVE LOGITS
     BitmapFactory
    0.64
    MetaType
    0.62
    expandindo
    0.58
     Influence
    0.55
    autoconfigure
    0.54
    GEBURTSDATUM
    0.54
    =$?
    0.53
    rrggbb
    0.53
    EDEFAULT
    0.53
     Einfluss
    0.52
    Activations Density 2.283%

    No Known Activations