© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16087
    Prev
    Next
    INDEX
    Explanations

    the word "topic" or "topics"

    oai_token-act-pair · gemini-2.0-flash

    topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     and
    -0.83
     the
    -0.69
    <bos>
    -0.67
    ↵↵
    -0.64
    ,
    -0.63
     for
    -0.60
     would
    -0.59
     will
    -0.57
     of
    -0.57
    kamer
    -0.56
    POSITIVE LOGITS
     Efq
    0.96
     Theſe
    0.94
     myſelf
    0.91
     Monfieur
    0.85
     Houſe
    0.85
     whoſe
    0.84
     himſelf
    0.81
     leaſt
    0.81
     becauſe
    0.81
     ſeveral
    0.80
    Activations Density 0.742%

    No Known Activations