© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1579
    Prev
    Next
    INDEX
    Explanations

    names, locations, dates and times from news articles, especially related to sports or finance

    oai_token-act-pair · gemini-2.0-flash

    Pra

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     Normdatei
    -1.02
    afficheront
    -0.84
    出版年
    -0.81
    存于互联网档案馆
    -0.77
    帖最后由
    -0.72
    GEBURTSDATUM
    -0.69
     auffi
    -0.66
     handleMessage
    -0.65
     useAuth
    -0.64
     Efq
    -0.63
    POSITIVE LOGITS
    DoubleQuotes
    0.57
    ("")]
    0.48
    }";
    0.44
    "}")
    0.43
    '};
    0.43
     Вікі
    0.42
    iffel
    0.42
    iration
    0.42
    }-
    0.42
     ("
    0.42
    Activations Density 7.364%

    No Known Activations