© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6907
    Prev
    Next
    INDEX
    Explanations

    descriptions of the shape, size, and nature of physical entities

    oai_token-act-pair · gemini-2.0-flash

    Describing physical properties

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     économique
    -0.56
     tâche
    -0.55
     médecine
    -0.54
     independientes
    -0.54
     poursuite
    -0.50
     énergé
    -0.50
     transferencia
    -0.49
     volna
    -0.49
    éndolo
    -0.48
     économiques
    -0.48
    POSITIVE LOGITS
     AssemblyProduct
    0.78
    DrawerToggle
    0.77
     AssemblyCulture
    0.73
    featureID
    0.71
    NameInMap
    0.71
    ]")]
    0.69
     Faso
    0.68
    ArgsConstructor
    0.68
     مرئيه
    0.68
     للاسماء
    0.66
    Activations Density 4.265%

    No Known Activations