© 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. 9425
    Prev
    Next
    INDEX
    Explanations

    references to wars, military groups, and locations involved in conflict

    oai_token-act-pair · gemini-2.0-flash

    conflicts and nations

    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
    mybatisplus
    -0.66
    MigrationBuilder
    -0.61
     MotionEvent
    -0.60
    TabStop
    -0.60
    contentLoaded
    -0.59
    labelledby
    -0.58
     переписи
    -0.57
    UnusedPrivate
    -0.56
     Blockly
    -0.54
    TagHelpers
    -0.54
    POSITIVE LOGITS
    Recon
    0.54
     Recon
    0.52
    <bos>
    0.48
     manqué
    0.47
     autorytatywna
    0.46
    recon
    0.44
     Waray
    0.44
    WebServlet
    0.43
     Paglinawan
    0.42
    ायक
    0.42
    Activations Density 8.870%

    No Known Activations