© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1511
    Prev
    Next
    INDEX
    Explanations

    Java or C# main method signatures

    oai_token-act-pair · gemini-2.0-flash

    Code/Exceptions

    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
    providedIn
    -0.57
    <bos>
    -0.56
    はじめに
    -0.54
    NULL
    -0.49
    ModelMap
    -0.48
     try
    -0.48
     Montrose
    -0.47
    cian
    -0.47
     tak
    -0.47
    merci
    -0.46
    POSITIVE LOGITS
    makeText
    0.54
    iNdEx
    0.52
    URLException
    0.50
    Tracce
    0.50
    yaszt
    0.49
    oredCriteria
    0.49
    NameInMap
    0.49
    ]--;
    0.49
     chi̍t
    0.48
    )}</
    0.48
    Activations Density 0.141%

    No Known Activations