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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7108
    Prev
    Next
    INDEX
    Explanations

    references to time, quantity, and historical context

    oai_token-act-pair · gemini-2.0-flash

    occasions/instances

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     site
    -1.09
    site
    -0.94
     Site
    -0.87
    Site
    -0.84
     website
    -0.78
     node
    -0.73
    SITE
    -0.71
     الموقع
    -0.69
    platform
    -0.69
     platform
    -0.68
    POSITIVE LOGITS
    MigrationBuilder
    0.75
     defaultstate
    0.70
     estekak
    0.70
    UnsafeEnabled
    0.69
    pushFollow
    0.65
    TestingModule
    0.58
    aarrggbb
    0.57
    Искәрмәләр
    0.57
     teacher
    0.55
    verwijspagina
    0.55
    Activations Density 5.839%

    No Known Activations