© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6484
    Prev
    Next
    INDEX
    Explanations

    locations, specifically San Diego and San Francisco, and URLs

    oai_token-act-pair · gemini-2.0-flash

    mentions of "San Diego"

    np_token-act-pair-logits · gpt-4o-mini

    San

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     doInBackground
    -0.60
     MonoBehaviour
    -0.53
    OpenHelper
    -0.52
     Revolución
    -0.50
    SqlSession
    -0.49
    спонд
    -0.49
    ORPG
    -0.49
    AndView
    -0.49
     onCreateView
    -0.48
    findpost
    -0.47
    POSITIVE LOGITS
    enumi
    0.61
     himo
    0.57
    numerusform
    0.55
     ويكيميديا
    0.54
     مشين
    0.53
     @"/
    0.52
    σθαι
    0.49
     Exacts
    0.48
     CURIAM
    0.48
    からです
    0.48
    Activations Density 0.106%

    No Known Activations