© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16056
    Prev
    Next
    INDEX
    Explanations

    Turkmen language, specifically names and locations, and also possibly medicine names referencing "-per-" and "zap-"

    oai_token-act-pair · gemini-2.0-flash

    Turkmen clubs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     kaynağından
    -0.63
     yapılan
    -0.50
    PerformLayout
    -0.50
     [*]
    -0.47
    爲
    -0.47
    diğinde
    -0.46
    ราย
    -0.44
    SEB
    -0.44
    MongoClient
    -0.44
     अधिक
    -0.43
    POSITIVE LOGITS
     ویکی‌پدیای
    0.88
    GEBURTSDATUM
    0.87
    WithIOException
    0.85
     GenerationType
    0.83
     للاسماء
    0.82
    Scénario
    0.74
     Normdatei
    0.74
    ьаж
    0.73
     صوتيه
    0.73
    oredCriteria
    0.72
    Activations Density 0.179%

    No Known Activations