© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15198
    Prev
    Next
    INDEX
    Explanations

    phrases that reference a specific time, especially years.

    oai_token-act-pair · gemini-2.0-flash

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    رسال
    -0.55
    еремо
    -0.53
    nością
    -0.53
    DebuggerStep
    -0.52
     von
    -0.52
     Ch
    -0.52
     Shi
    -0.50
     Von
    -0.50
    riba
    -0.50
     rész
    -0.50
    POSITIVE LOGITS
    tagHelperRunner
    0.77
    ագրություններ
    0.65
    }');
    0.64
    styleType
    0.61
    ViewFeatures
    0.60
    enumii
    0.59
    tableFuture
    0.59
     itſelf
    0.58
    mybatisplus
    0.57
    RegressionTest
    0.57
    Activations Density 0.874%

    No Known Activations