© 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. 1369
    Prev
    Next
    INDEX
    Explanations

    discourse about cybersecurity and political attacks.

    oai_token-act-pair · gemini-2.0-flash

    sabotage

    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
     l
    -0.38
    ,
    -0.36
     I
    -0.35
     V
    -0.35
     co
    -0.35
     express
    -0.35
     (
    -0.34
     en
    -0.34
    Abp
    -0.34
     
    -0.34
    POSITIVE LOGITS
    ReusableCell
    1.04
     فريبيس
    1.03
    SourceChecksum
    1.01
    UserScript
    0.92
     تضيفلها
    0.91
     auffi
    0.90
    InjectAttribute
    0.84
     estekak
    0.81
    GEBURTSDATUM
    0.81
     iſt
    0.81
    Activations Density 2.887%

    No Known Activations