© 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. 13216
    Prev
    Next
    INDEX
    Explanations

    locations like towns and cities with associated words like "in", "to", and "the"

    oai_token-act-pair · gemini-2.0-flash

    Locations and events

    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
    afficheront
    -0.50
     arco
    -0.46
     st
    -0.40
    ms
    -0.40
    SHARE
    -0.40
    ra
    -0.40
    ham
    -0.40
    チュア
    -0.40
     b
    -0.39
    erializer
    -0.39
    POSITIVE LOGITS
     Efq
    0.90
    Personensuche
    0.80
    UrlResolution
    0.77
     myſelf
    0.77
     saites
    0.75
     himſelf
    0.73
     Monfieur
    0.71
     Jefus
    0.71
     itſelf
    0.71
     ་་
    0.71
    Activations Density 1.338%

    No Known Activations