© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10507
    Prev
    Next
    INDEX
    Explanations

    technical documents or academic papers

    oai_token-act-pair · 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
     Diony
    -0.61
    Демографія
    -0.59
    pesar
    -0.54
     Lordships
    -0.54
     Vettel
    -0.54
    <!--[
    -0.54
     censiti
    -0.54
     gewisse
    -0.51
    حياته
    -0.50
     dynamically
    -0.50
    POSITIVE LOGITS
     BorderLayout
    0.64
     onAnimation
    0.53
    κτηρισ
    0.52
    MigrationBuilder
    0.50
     Beam
    0.50
    edon
    0.48
    ǒ
    0.48
     MonoBehaviour
    0.47
    prepareStatement
    0.46
     TOPOLOGY
    0.46
    Activations Density 13.087%

    No Known Activations