© 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
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 7002
    Prev
    Next
    INDEX
    Explanations

    text related to scientific research reports including grant numbers, study identifiers, acronyms, and ethical approvals.

    oai_token-act-pair · gemini-2.0-flash

    Dutch references

    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
     Chriftian
    -0.96
     Majefty
    -0.89
     Houſe
    -0.87
     houſe
    -0.85
     Monfieur
    -0.84
     pleaſure
    -0.81
     purpoſe
    -0.80
     Theſe
    -0.79
     ſeveral
    -0.79
     Efq
    -0.79
    POSITIVE LOGITS
     van
    0.65
    verwijspagina
    0.59
     Van
    0.53
    Voor
    0.52
    rij
    0.52
     Bakker
    0.51
    __':
    0.50
     Bij
    0.50
     Dutch
    0.49
     Amsterdam
    0.49
    Activations Density 19.068%

    No Known Activations