© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13836
    Prev
    Next
    INDEX
    Explanations

    short words that often appear in biographical and historical texts, such as dates, family relations, and lineage.

    oai_token-act-pair · gemini-2.0-flash

    Biographical information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ItemBackground
    -0.71
    WriteBarrier
    -0.67
     Roskov
    -0.66
    ANDUM
    -0.65
     Normdatei
    -0.65
    twimg
    -0.63
    RegistryLite
    -0.62
     feroit
    -0.61
    AsUp
    -0.61
    BeginInit
    -0.61
    POSITIVE LOGITS
     Capp
    0.46
     coba
    0.45
     aca
    0.44
    bibitem
    0.44
    出版年
    0.44
    <?
    0.43
    INES
    0.43
    illy
    0.43
     Clement
    0.43
     bar
    0.42
    Activations Density 0.903%

    No Known Activations