© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13158
    Prev
    Next
    INDEX
    Explanations

    terms related to databases, software development, and configurations

    oai_token-act-pair · gemini-2.0-flash

    software/database development

    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
    हाय
    -0.47
    ViewImports
    -0.46
     Chaves
    -0.45
    bunga
    -0.43
    ีย์
    -0.43
    vég
    -0.43
    CUIT
    -0.42
    vaz
    -0.40
     }}"
    -0.40
    ureka
    -0.39
    POSITIVE LOGITS
    出版年
    0.69
     Réponses
    0.69
    SBATCH
    0.68
    tvguidetime
    0.68
    AnimationsModule
    0.68
    LookAnd
    0.65
    Nationalité
    0.63
    Clik
    0.61
     TimeUnit
    0.61
    CloseOperation
    0.61
    Activations Density 1.048%

    No Known Activations