© 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. 9783
    Prev
    Next
    INDEX
    Explanations

    references to position relative to some object

    oai_token-act-pair · gemini-2.0-flash

    south, opening

    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
     lourdes
    -0.93
     étoit
    -0.92
     scolas
    -0.91
     fausse
    -0.90
     sexuelle
    -0.89
     irré
    -0.89
     feroit
    -0.88
     sauvages
    -0.88
     héro
    -0.87
     umana
    -0.87
    POSITIVE LOGITS
    ,
    0.71
    ArrowToggle
    0.64
    ‍♂️
    0.59
    Rüyada
    0.58
     جغرافيا
    0.49
     –
    0.49
    .";
    0.47
    __":
    0.46
    demment
    0.46
    /
    0.46
    Activations Density 1.998%

    No Known Activations