© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11637
    Prev
    Next
    INDEX
    Explanations

    the conjunction 'and', though it also has some activity related to commas and dialogue

    oai_token-act-pair · gemini-2.0-flash

    and

    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
     the
    -0.90
     it
    -0.85
     its
    -0.78
     a
    -0.77
     I
    -0.73
     an
    -0.71
     to
    -0.68
     for
    -0.66
     [
    -0.66
     my
    -0.65
    POSITIVE LOGITS
     myſelf
    1.19
     pleaſure
    1.02
     purpoſe
    1.02
     itſelf
    1.01
     Efq
    0.99
     Jefus
    0.98
     houſe
    0.95
     Monfieur
    0.94
     auroit
    0.93
    ſelves
    0.92
    Activations Density 1.339%

    No Known Activations