© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13015
    Prev
    Next
    INDEX
    Explanations

    the city name "Goshen"

    oai_token-act-pair · gemini-2.0-flash

    Incorporated

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     kasarigan
    -0.70
     المعيارى
    -0.69
    HtmlAttribute
    -0.65
     intptr
    -0.65
    Naissance
    -0.63
    SOUNDBITE
    -0.62
    ViewFeatures
    -0.62
    pexpr
    -0.61
    ModelAdmin
    -0.61
    saraba
    -0.60
    POSITIVE LOGITS
     INCORPOR
    0.79
    corporated
    0.77
     incorporated
    0.75
     incorpor
    0.71
     incorporation
    0.71
     Incorporated
    0.70
     corporate
    0.69
     Incorpor
    0.68
     Incorporation
    0.64
    corporate
    0.61
    Activations Density 1.669%

    No Known Activations