© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15988
    Prev
    Next
    INDEX
    Explanations

    words or phrases that refer to detractors

    oai_token-act-pair · gemini-2.0-flash

    critics

    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
    )");
    -0.64
    ourites
    -0.64
    alised
    -0.62
    rigues
    -0.61
    )";
    -0.60
    ategorised
    -0.60
    )"),
    -0.59
    Zeneca
    -0.57
    cherichia
    -0.57
    Organiser
    -0.57
    POSITIVE LOGITS
     resourceCulture
    0.76
     skjer
    0.73
    دانشنامهٔ
    0.70
     otomatig
    0.68
     eccl
    0.63
     houſe
    0.63
     Greeks
    0.62
     Reſ
    0.62
     Grecs
    0.61
    vyk
    0.60
    Activations Density 1.570%

    No Known Activations