© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10547
    Prev
    Next
    INDEX
    Explanations

    proper nouns and phrases naming particular places

    oai_token-act-pair · gemini-2.0-flash

    industrial/commercial locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    ProgressHUD
    -0.61
    greSQL
    -0.53
     IBOutlet
    -0.52
    bootstrapcdn
    -0.52
    othelioma
    -0.51
    dieu
    -0.51
    [@"
    -0.51
    TabbedPane
    -0.50
    atamente
    -0.49
     sepak
    -0.49
    POSITIVE LOGITS
    basicConfig
    0.70
     city
    0.55
    Viited
    0.53
    __(/*!
    0.51
    Lähteet
    0.51
     Савезне
    0.50
    eterangan
    0.50
    AddTagHelper
    0.49
    +#+
    0.48
    Życiorys
    0.48
    Activations Density 3.072%

    No Known Activations