© 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. 14945
    Prev
    Next
    INDEX
    Explanations

    words related to violence

    oai_token-act-pair · gemini-2.0-flash

    violence/killing

    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
    FieldNumber
    -0.54
    CodedInputStream
    -0.53
    InstrumentedTest
    -0.52
     дописавши
    -0.51
    principalColumn
    -0.51
    ContextCompat
    -0.49
     Alamy
    -0.48
    uxxxx
    -0.48
     tunt
    -0.48
    ecore
    -0.48
    POSITIVE LOGITS
    SBATCH
    0.54
    Descripció
    0.50
    ividu
    0.49
    रीदारी
    0.49
    pageTitle
    0.49
    ftagPool
    0.49
    XmlAccessorType
    0.48
    interopRequire
    0.47
    好不容易
    0.47
     consulter
    0.46
    Activations Density 1.245%

    No Known Activations