© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11012
    Prev
    Next
    INDEX
    Explanations

    Sanskrit terms, especially those related to religion and deities

    oai_token-act-pair · gemini-2.0-flash

    Narasimha

    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
    tidaknya
    -0.58
    RLock
    -0.55
     contextLoads
    -0.55
     Bourgoin
    -0.53
    ThroughAttribute
    -0.53
     Directeur
    -0.50
    TypedDataSet
    -0.50
     verhe
    -0.50
    ISPR
    -0.50
     Galveston
    -0.49
    POSITIVE LOGITS
     Audiodateien
    0.62
    agrama
    0.59
    Collegamenti
    0.59
     kasarigan
    0.55
     ujednoznacz
    0.54
    RenderAtEndOf
    0.53
     CreateTagHelper
    0.52
    Corollary
    0.52
     "..\..\..\
    0.52
     pe
    0.52
    Activations Density 0.746%

    No Known Activations