© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1301
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to violent conflict, medical emergencies, and law enforcement activity.

    oai_token-act-pair · gemini-2.0-flash

    violence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     security
    -0.68
    ruptedException
    -0.65
     vulnerable
    -0.65
    CppCodeGen
    -0.60
    MIDDLEWARE
    -0.60
    atimes
    -0.59
     Normdatei
    -0.59
    Sicherheit
    -0.58
     unprotected
    -0.58
    новниш
    -0.58
    POSITIVE LOGITS
    <bos>
    0.58
    amqp
    0.50
    исленность
    0.49
    TSCA
    0.47
     iscri
    0.46
    NH
    0.45
    reams
    0.45
     Nimbus
    0.43
    obenz
    0.43
    chein
    0.43
    Activations Density 1.299%

    No Known Activations