© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6342
    Prev
    Next
    INDEX
    Explanations

    terms in written arguments, including logical connectors, legal terms, and value judgements.

    oai_token-act-pair · gemini-2.0-flash

    Code/technical discussions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    })()
    -0.62
    RouterModule
    -0.47
    ården
    -0.47
    %");
    -0.47
    AppComponent
    -0.45
    immutable
    -0.45
    QWidget
    -0.43
     Mohr
    -0.42
     doméstica
    -0.42
     [],
    -0.41
    POSITIVE LOGITS
    RegressionTest
    0.86
    TargetException
    0.83
    TagMode
    0.76
    ########.
    0.75
    StructEnd
    0.73
     متعلقه
    0.72
     kasarigan
    0.72
    fjspx
    0.71
    IndentedString
    0.71
     estekak
    0.69
    Activations Density 5.833%

    No Known Activations