© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10620
    Prev
    Next
    INDEX
    Explanations

    capitalized short words, particularly those relating to products, models, or species

    oai_token-act-pair · gemini-2.0-flash

    technology fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     descrição
    -0.44
     giáp
    -0.44
     responsáveis
    -0.43
     frequência
    -0.43
    proc
    -0.41
    stor
    -0.41
    ritt
    -0.41
    coe
    -0.41
    fen
    -0.41
    рой
    -0.41
    POSITIVE LOGITS
     nakalista
    0.72
    Portail
    0.71
    يكب
    0.70
    IsContent
    0.69
    VersionUID
    0.69
     виправивши
    0.69
     localVar
    0.68
    GeneratedMessage
    0.67
    TagMode
    0.67
    ScopeManager
    0.66
    Activations Density 1.004%

    No Known Activations