© 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. 16331
    Prev
    Next
    INDEX
    Explanations

    titles, headings, and dates in technical documents related to medicine, science, and education

    oai_token-act-pair · gemini-2.0-flash

    new

    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
    ArrowToggle
    -0.94
    Bibliograf
    -0.65
    ########.
    -0.65
    šinou
    -0.58
    >{@
    -0.58
    السكان
    -0.56
    webElementXpaths
    -0.56
    DrawerToggle
    -0.55
    queryInterface
    -0.54
     ComVisible
    -0.54
    POSITIVE LOGITS
     New
    3.73
    New
    3.41
     Nueva
    2.06
     NEW
    2.03
    NEW
    1.96
     Новый
    1.84
    Nueva
    1.77
     Nuevo
    1.70
     Nouvelle
    1.69
    NewUser
    1.57
    Activations Density 7.997%

    No Known Activations