© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3346
    Prev
    Next
    INDEX
    Explanations

    acknowledgements, conversational fillers, and section markers

    oai_token-act-pair · gemini-2.0-flash

    variations of "okay"

    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
     '\\;'
    -0.93
    abstractmethod
    -0.75
    DrawerToggle
    -0.73
     Efq
    -0.73
     tartalomajánló
    -0.71
    EnableWeb
    -0.71
    IVEREF
    -0.71
    AddHtmlAttribute
    -0.70
     ligiloj
    -0.70
    expandindo
    -0.69
    POSITIVE LOGITS
     so
    2.17
     So
    1.65
    So
    1.62
    so
    1.56
     OK
    1.19
     ok
    1.17
     okay
    1.11
     SO
    1.10
     так
    1.09
     så
    1.05
    Activations Density 2.058%

    No Known Activations