© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 205
    Prev
    Next
    INDEX
    Explanations

    C# code syntax, specifically the "using" keyword, file extension delimiters, and auto-generated code tags

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    });*/
    -0.54
     Nub
    -0.50
    ?\
    -0.47
    ting
    -0.47
    Tw
    -0.47
    ++
    -0.47
    %?
    -0.46
    .。
    -0.46
     }}=\
    -0.46
     ESM
    -0.46
    POSITIVE LOGITS
    XmlAccessType
    0.94
    RegistryLite
    0.94
     defaultstate
    0.87
    MigrationBuilder
    0.86
    mybatisplus
    0.82
    HasColumnType
    0.79
    الدراسه
    0.78
    DockStyle
    0.77
    sizeCache
    0.77
    mergeFrom
    0.77
    Activations Density 9.199%

    No Known Activations