© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13021
    Prev
    Next
    INDEX
    Explanations

    many different kinds of phrases about links to sources, organizations giving information and identifying people

    oai_token-act-pair · gemini-2.0-flash

    article excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     تضيفلها
    -0.57
    archiviato
    -0.52
    /*++
    -0.46
     direct
    -0.45
     function
    -0.45
     Thread
    -0.45
     lisäksi
    -0.45
     chiếu
    -0.44
    FontWeight
    -0.44
     but
    -0.44
    POSITIVE LOGITS
    StoryboardSegue
    0.75
     tartalomajánló
    0.61
     للاسماء
    0.57
    parsedMessage
    0.57
    IsContent
    0.56
     sandero
    0.56
     Paroles
    0.55
    ViewImports
    0.54
    tanleria
    0.52
    Бахар
    0.52
    Activations Density 0.541%

    No Known Activations