© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10395
    Prev
    Next
    INDEX
    Explanations

    words from different languages and code

    oai_token-act-pair · gemini-2.0-flash

    Non-English language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    ↵↵
    -0.68
    <bos>
    -0.62
    .
    -0.61
    ,
    -0.54
    (
    -0.51
     to
    -0.47
     for
    -0.46
    abetes
    -0.45
    }
    -0.45
    -
    -0.44
    POSITIVE LOGITS
     виправивши
    0.92
    SourceChecksum
    0.90
    ьаж
    0.87
    queryInterface
    0.85
    aarrggbb
    0.84
     propOrder
    0.82
    setVerticalGroup
    0.82
    DotNetBar
    0.81
     "..\..\..\
    0.78
     himo
    0.77
    Activations Density 13.812%

    No Known Activations