© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3785
    Prev
    Next
    INDEX
    Explanations

    the "Mor" prefix

    oai_token-act-pair · gemini-2.0-flash

    Mor

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     springfox
    -0.73
    ViewImports
    -0.71
     étrangère
    -0.61
     productivo
    -0.61
    subpackage
    -0.61
     VIAF
    -0.61
     CURIAM
    -0.61
     QWidget
    -0.60
    QWidget
    -0.60
    rollup
    -0.60
    POSITIVE LOGITS
     \%)$
    0.51
    Pautan
    0.46
    спонд
    0.43
     Khor
    0.42
    osidad
    0.41
     للاسماء
    0.41
    ]))
    0.41
     Twit
    0.39
    _));
    0.39
    als
    0.39
    Activations Density 0.492%

    No Known Activations