© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12746
    Prev
    Next
    INDEX
    Explanations

    words that are related to roles or components of a set or process

    oai_token-act-pair · gemini-2.0-flash

    part

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    ]}>
    -0.50
    )?.
    -0.47
    odils
    -0.43
    indelijk
    -0.43
     comfor
    -0.43
    >');
    -0.43
    namics
    -0.43
    </strong>
    -0.43
    ]>=
    -0.42
    ]._
    -0.42
    POSITIVE LOGITS
    expandindo
    0.85
    ItemBackground
    0.80
     مشين
    0.77
    تقاوى
    0.73
     intptr
    0.72
     كومونز
    0.71
    featureID
    0.70
    HtmlAttribute
    0.70
    RenderAtEndOf
    0.66
    fjspx
    0.65
    Activations Density 2.580%

    No Known Activations