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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7063
    Prev
    Next
    INDEX
    Explanations

    words related to time, reporting, and locations, particularly in the context of issues or planning, especially involving roads, public works, or property.

    oai_token-act-pair · gemini-2.0-flash

    next

    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
    usermodel
    -0.72
     fall
    -0.59
    οιν
    -0.52
    יקר
    -0.51
    fall
    -0.49
    chila
    -0.49
    ⎢
    -0.48
    FieldBuilder
    -0.47
     Fall
    -0.47
     CALENDAR
    -0.46
    POSITIVE LOGITS
    AnimationsModule
    0.62
     שוליים
    0.60
    providedIn
    0.59
     actionPerformed
    0.58
    CppMethod
    0.58
    </tfoot>
    0.55
    AxisAlignment
    0.52
    AndroidJUnit
    0.52
    GraphicsUnit
    0.52
    DotNetBar
    0.52
    Activations Density 9.559%

    No Known Activations