© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5225
    Prev
    Next
    INDEX
    Explanations

    descriptions of tourist destinations and attractions

    oai_token-act-pair · gemini-2.0-flash

    Travel and visiting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    
    -0.77
    __*/
    -0.66
     defaultstate
    -0.64
    FunctionFlags
    -0.62
    WebVitals
    -0.60
    __":
    -0.59
     '\\;'
    -0.59
    ImageContext
    -0.58
     AssemblyVersion
    -0.58
    ContentAsync
    -0.57
    POSITIVE LOGITS
     visit
    0.93
     visited
    0.85
    visit
    0.76
     watch
    0.74
     visits
    0.73
     visiting
    0.73
     VISIT
    0.71
     watched
    0.71
     explore
    0.70
     Visit
    0.70
    Activations Density 2.136%

    No Known Activations