© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12001
    Prev
    Next
    INDEX
    Explanations

    geographic locations in Alaska and distances between them

    oai_token-act-pair · gemini-2.0-flash

    Alaska locations

    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
    Referanser
    -0.50
    FXMLLoader
    -0.45
    me
    -0.43
     me
    -0.43
    md
    -0.41
    ключи
    -0.41
    Basic
    -0.41
     ouder
    -0.41
    AppData
    -0.40
    meti
    -0.39
    POSITIVE LOGITS
    новниш
    0.77
     IBOutlet
    0.67
    Personendaten
    0.64
    hoots
    0.59
    EnableWeb
    0.58
    CreateModel
    0.57
    
    0.57
     Comstock
    0.56
    expandindo
    0.56
    Herzliche
    0.56
    Activations Density 1.192%

    No Known Activations