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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11877
    Prev
    Next
    INDEX
    Explanations

    words related to time and mathematical simulations

    oai_token-act-pair · gemini-2.0-flash

    evolution, steps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    ülle
    -0.52
     chút
    -0.52
     AssemblyProduct
    -0.49
    houettes
    -0.49
    sendFile
    -0.48
    Portail
    -0.47
    Lugares
    -0.46
    azan
    -0.46
     Verhältnis
    -0.46
     Beziehungen
    -0.44
    POSITIVE LOGITS
    providedIn
    0.77
    ActionCreators
    0.69
     OnTrigger
    0.67
    انجليز
    0.65
    SaveChangesAsync
    0.63
    Carriera
    0.61
    DeleteBehavior
    0.60
    runApp
    0.60
     FixedUpdate
    0.59
     estekak
    0.59
    Activations Density 2.579%

    No Known Activations