© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6265
    Prev
    Next
    INDEX
    Explanations

    the word "course," especially when preceded by "of."

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    EFIAPI
    -0.62
    RenderAtEndOf
    -0.61
    زال
    -0.60
    WithIOException
    -0.59
    gae
    -0.55
     ligiloj
    -0.52
     IBOutlet
    -0.52
     Ersten
    -0.52
    ViewFeatures
    -0.52
    forRoot
    -0.52
    POSITIVE LOGITS
     ovviamente
    1.23
     obviously
    1.16
     obviamente
    1.13
    obviously
    1.05
     ofc
    1.05
     naturalmente
    1.00
     évidemment
    0.99
     Obviously
    0.96
     course
    0.96
     natürlich
    0.93
    Activations Density 1.018%

    No Known Activations