© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 424
    Prev
    Next
    INDEX
    Explanations

    references to the Soviet Union/Nazi Germany and surrounding political concepts

    oai_token-act-pair · gemini-2.0-flash

    Soviet Union, Cold War

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     post
    -0.65
    post
    -0.65
     timur
    -0.59
    Post
    -0.58
     Post
    -0.54
     drop
    -0.54
    POST
    -0.54
    ure
    -0.54
     na
    -0.53
     POST
    -0.52
    POSITIVE LOGITS
     wireType
    0.68
     AssemblyTitle
    0.66
    AtIndexPath
    0.63
     ErrIntOverflow
    0.59
     BrowserModule
    0.58
    jména
    0.57
    HandlerContext
    0.55
    maxcdn
    0.55
     doInBackground
    0.54
     ***!
    0.54
    Activations Density 2.274%

    No Known Activations