© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4852
    Prev
    Next
    INDEX
    Explanations

    the term "abuse."

    oai_token-act-pair · gemini-2.0-flash

    abuse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     abuse
    -2.20
     Abuse
    -1.83
    abuse
    -1.77
     abused
    -1.62
    Abuse
    -1.61
     abusing
    -1.52
     abuses
    -1.43
     abuso
    -1.34
     abus
    -1.30
     abusive
    -1.20
    POSITIVE LOGITS
    oredCriteria
    0.85
    Personensuche
    0.82
     المعيارى
    0.80
    ]")]
    0.79
    Tembelea
    0.77
    tagHelperRunner
    0.77
     pinulongan
    0.76
     nahilalakip
    0.75
    PMailer
    0.74
    findpost
    0.74
    Activations Density 0.760%

    No Known Activations