© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11000
    Prev
    Next
    INDEX
    Explanations

    words possibly related to travel and/or Seville, Spain

    oai_token-act-pair · gemini-2.0-flash

    tourist destinations

    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
    :✨
    -0.68
    ContentAsync
    -0.60
     referenties
    -0.58
    ConstraintMaker
    -0.56
     PropertyChanged
    -0.56
    Oph
    -0.54
    ofis
    -0.52
     Roumanie
    -0.51
    CompleteListener
    -0.49
    Personensuche
    -0.48
    POSITIVE LOGITS
    fulness
    0.58
    Sucesor
    0.58
     bars
    0.57
    Narrow
    0.56
    narrow
    0.52
     Narrow
    0.52
    eaky
    0.52
     cob
    0.51
     Faso
    0.51
    bars
    0.50
    Activations Density 0.856%

    No Known Activations