© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2785
    Prev
    Next
    INDEX
    Explanations

    hedging language, alternatives, and references to medical trials

    oai_token-act-pair · gemini-2.0-flash

    logical relationships

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     non
    -1.30
     Non
    -1.11
    Non
    -1.11
    non
    -1.00
     NON
    -0.98
     nons
    -0.92
    NON
    -0.88
    非
    -0.87
    nons
    -0.82
     Nons
    -0.78
    POSITIVE LOGITS
     Seeder
    0.73
    }],
    0.71
    SequentialGroup
    0.69
     مرئيه
    0.65
    sizeCache
    0.65
    URLException
    0.63
    oa̍t
    0.61
    
    0.61
     démission
    0.60
    RegressionTest
    0.59
    Activations Density 8.426%

    No Known Activations