© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1871
    Prev
    Next
    INDEX
    Explanations

    mentions of Chinese history, specifically the Shu Han dynasty and the Cao Wei kingdom.

    oai_token-act-pair · gemini-2.0-flash

    Han

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    protoimpl
    -0.69
    enderror
    -0.64
     Paglinawan
    -0.62
    thâu
    -0.59
    Jeografia
    -0.59
    Notae
    -0.57
     Quill
    -0.57
    piram
    -0.56
    ğraf
    -0.55
    filepath
    -0.54
    POSITIVE LOGITS
    //
    0.57
    multirow
    0.50
    HINT
    0.43
    шаем
    0.43
    }^{+\
    0.43
    <_>
    0.42
     BigNumberish
    0.42
    ArgsConstructor
    0.42
    لیس
    0.41
    Hint
    0.41
    Activations Density 1.815%

    No Known Activations