© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13771
    Prev
    Next
    INDEX
    Explanations

    scientific names for insects or animals

    oai_token-act-pair · gemini-2.0-flash

    family

    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
    Tembelea
    -0.86
    WebServlet
    -0.82
    AxisAlignment
    -0.77
     jadx
    -0.76
     estekak
    -0.76
    EndContext
    -0.75
    orari
    -0.72
    MarshalTo
    -0.71
    MultipartFile
    -0.71
    */;
    -0.71
    POSITIVE LOGITS
     durata
    0.49
     précédentes
    0.46
     sueños
    0.45
    principalColumn
    0.44
     distância
    0.44
     prochains
    0.44
     atualização
    0.43
     brancas
    0.43
     distribuição
    0.42
     PO
    0.42
    Activations Density 0.414%

    No Known Activations