© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 763
    Prev
    Next
    INDEX
    Explanations

    field names and their values inside curly braces, possibly in JSON or a similar data format

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     ſeveral
    -0.56
     tassels
    -0.51
     Monfieur
    -0.50
     surla
    -0.49
     islets
    -0.49
     dialects
    -0.49
    
    -0.48
     myſelf
    -0.48
     pleaſure
    -0.47
     icing
    -0.46
    POSITIVE LOGITS
    AFX
    0.69
    FFFFFFFF
    0.68
     estekak
    0.68
    +#+#
    0.67
    writeFieldEnd
    0.66
    __':
    0.65
    FZ
    0.64
    MF
    0.62
    ?}",
    0.61
    qrstuvwxyz
    0.61
    Activations Density 35.733%

    No Known Activations