© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9921
    Prev
    Next
    INDEX
    Explanations

    place names, designer titles and funding acknowledgements

    oai_token-act-pair · gemini-2.0-flash

    Random text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    })_{
    -0.62
    thâu
    -0.56
     Yay
    -0.56
    MENAFN
    -0.56
     Fathers
    -0.54
    }()
    -0.54
    moduleId
    -0.52
     excitations
    -0.52
    yntaxException
    -0.52
    EndProject
    -0.52
    POSITIVE LOGITS
    TRIBUN
    0.58
     QWidget
    0.48
    ykjav
    0.47
    fony
    0.47
     NSCoder
    0.46
    хьтан
    0.46
    struktion
    0.45
    rensen
    0.45
    AFX
    0.44
    שק
    0.44
    Activations Density 0.350%

    No Known Activations