© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6069
    Prev
    Next
    INDEX
    Explanations

    words related to negative online behavior and medical terms

    oai_token-act-pair · gemini-2.0-flash

    insults and hatred

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    Skocz
    -0.49
     preci
    -0.45
    matchCondition
    -0.44
     rivets
    -0.43
     forsaken
    -0.41
    contexts
    -0.41
     vér
    -0.41
    gnąć
    -0.40
     consulté
    -0.40
    angkap
    -0.40
    POSITIVE LOGITS
     slander
    1.02
     insults
    0.94
     defamation
    0.90
     smear
    0.87
     hate
    0.83
     hatred
    0.83
     attacks
    0.82
     insulting
    0.81
     insult
    0.81
     calum
    0.81
    Activations Density 1.795%

    No Known Activations