© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9115
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives indicating quality or importance

    oai_token-act-pair · gemini-2.0-flash

    importance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ConstraintMaker
    -0.64
    omitempty
    -0.62
    WireFormatLite
    -0.61
    Personendaten
    -0.55
    etCode
    -0.54
    ValueStyle
    -0.54
    IBOutlet
    -0.53
     ujednoznacz
    -0.53
     CWE
    -0.51
    idste
    -0.49
    POSITIVE LOGITS
     חיצוניים
    0.57
    maq
    0.50
    koper
    0.50
    κτη
    0.48
    {}{}
    0.48
    /";
    0.46
     endwhile
    0.46
    ArgumentParser
    0.46
    parsedMessage
    0.44
    errated
    0.43
    Activations Density 0.942%

    No Known Activations