© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10360
    Prev
    Next
    INDEX
    Explanations

    words related to research, studies, and scientific findings, often including experimental procedures or results

    oai_token-act-pair · gemini-2.0-flash

    transitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Monfieur
    -0.87
     auroit
    -0.83
     feroit
    -0.83
     Efq
    -0.82
     itſelf
    -0.81
     Theſe
    -0.81
    ientôt
    -0.80
     ſeveral
    -0.79
     كومونز
    -0.78
     Reſ
    -0.78
    POSITIVE LOGITS
    <bos>
    1.23
    ↵
    0.84
    ↵↵
    0.80
    <h4>
    0.62
     
    0.55
      
    0.54
    HtmlAttribute
    0.54
    -
    0.54
    <h3>
    0.54
    <h2>
    0.53
    Activations Density 4.709%

    No Known Activations